asset: 归档第一集已生成镜头与测试素材,排除可再生缓存

This commit is contained in:
2026-10-01 00:35:36 +08:00
parent 0da2659df2
commit f900237d96
1719 changed files with 264761 additions and 0 deletions
@@ -0,0 +1,18 @@
{
"prompt_id": "49e0cb0c-b103-4101-a8b1-dcbf0b776944",
"number": 95,
"node_errors": {},
"seed": 246089913781214,
"frames": 124,
"width": 960,
"height": 544,
"submitted_at": 1790658384.8124938,
"shot": {
"id": "C01",
"image": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\frames\\C01.png",
"seconds": 5,
"edit_seconds": 5,
"prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. A tiny slow Push In toward the half-full water glass, only 3 percent over the shot. The cream fan blades rotate evenly behind its absolutely rigid grille; the fan base stays still. A soft airflow slightly lifts the translucent curtain hem and makes just the uppermost mint leaves sway with different phases. Sunlight trembles subtly through leaves onto the desk. Everything else keeps its shape. No people, no speech.\n\noverall_soundscape: Soft steady electric fan motor and a faint intermittent bearing tick, very distant daytime city ambience. No voices.\n\nnon_diegetic_music: None.",
"dialogue": ""
}
}
@@ -0,0 +1,13 @@
{
"summary": "nodes=16 edges=19 overlaps=0 crossings=9 bounds=[40, 40, 3490, 2692]",
"overlaps": [],
"crossings": 9,
"bounds": [
40.0,
40.0,
3490.0,
2692.0
],
"n_nodes": 16,
"n_edges": 19
}
@@ -0,0 +1,3 @@
[
"F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C01\\C01_V01_00001_.mp4"
]
@@ -0,0 +1,7 @@
For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
integrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. A tiny slow Push In toward the half-full water glass, only 3 percent over the shot. The cream fan blades rotate evenly behind its absolutely rigid grille; the fan base stays still. A soft airflow slightly lifts the translucent curtain hem and makes just the uppermost mint leaves sway with different phases. Sunlight trembles subtly through leaves onto the desk. Everything else keeps its shape. No people, no speech.
overall_soundscape: Soft steady electric fan motor and a faint intermittent bearing tick, very distant daytime city ambience. No voices.
non_diegetic_music: None.
Binary file not shown.

After

Width:  |  Height:  |  Size: 1.2 MiB

@@ -0,0 +1,6 @@
{
"expected": "",
"recognized": "",
"segments": [],
"note": "ASR transcription, not a listening certification."
}
@@ -0,0 +1,5 @@
{
"prompt_id": "49e0cb0c-b103-4101-a8b1-dcbf0b776944",
"number": 95,
"node_errors": {}
}
@@ -0,0 +1,181 @@
{
"1": {
"class_type": "LoadImage",
"inputs": {
"image": "hearthfire_h3/C01_C01.png"
}
},
"2": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"weight_dtype": "default"
}
},
"3": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"model": [
"2",
0
],
"lora_name": "minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
"strength_model": 1.0
}
},
"4": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"type": "minimax",
"device": "default"
}
},
"5": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "minimax_h3_video_vae_fp16.safetensors"
}
},
"6": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "minimax_h3_audio_vae_fp32.safetensors"
}
},
"7": {
"class_type": "MiniMaxH3ImageToVideo",
"inputs": {
"clip": [
"4",
0
],
"vae": [
"5",
0
],
"first_frame": [
"1",
0
],
"prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. A tiny slow Push In toward the half-full water glass, only 3 percent over the shot. The cream fan blades rotate evenly behind its absolutely rigid grille; the fan base stays still. A soft airflow slightly lifts the translucent curtain hem and makes just the uppermost mint leaves sway with different phases. Sunlight trembles subtly through leaves onto the desk. Everything else keeps its shape. No people, no speech.\n\noverall_soundscape: Soft steady electric fan motor and a faint intermittent bearing tick, very distant daytime city ambience. No voices.\n\nnon_diegetic_music: None.",
"width": 960,
"height": 544,
"length": 124
}
},
"8": {
"class_type": "BasicGuider",
"inputs": {
"model": [
"3",
0
],
"conditioning": [
"7",
0
]
}
},
"9": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 246089913781214
}
},
"10": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "res_multistep"
}
},
"11": {
"class_type": "BasicScheduler",
"inputs": {
"model": [
"3",
0
],
"scheduler": "simple",
"steps": 8,
"denoise": 1.0
}
},
"12": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"noise": [
"9",
0
],
"guider": [
"8",
0
],
"sampler": [
"10",
0
],
"sigmas": [
"11",
0
],
"latent_image": [
"7",
1
]
}
},
"13": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"12",
0
],
"vae": [
"5",
0
]
}
},
"14": {
"class_type": "VAEDecodeAudio",
"inputs": {
"samples": [
"12",
0
],
"vae": [
"6",
0
]
}
},
"15": {
"class_type": "CreateVideo",
"inputs": {
"images": [
"13",
0
],
"audio": [
"14",
0
],
"fps": 24.0
}
},
"16": {
"class_type": "SaveVideo",
"inputs": {
"video": [
"15",
0
],
"filename_prefix": "hearthfire_episode/C01_V01",
"format": "mp4",
"codec": "h264"
}
}
}
@@ -0,0 +1,804 @@
{
"last_node_id": 16,
"last_link_id": 19,
"nodes": [
{
"id": 1,
"type": "LoadImage",
"pos": [
40,
1890
],
"size": [
390,
432
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
4
]
},
{
"name": "MASK",
"type": "MASK",
"links": []
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"hearthfire_h3/C01_C01.png",
"image"
]
},
{
"id": 2,
"type": "UNETLoader",
"pos": [
40,
40
],
"size": [
390,
300
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
1
]
}
],
"properties": {
"Node name for S&R": "UNETLoader"
},
"widgets_values": [
"minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"default"
]
},
{
"id": 3,
"type": "LoraLoaderModelOnly",
"pos": [
550,
964
],
"size": [
390,
300
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 1
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
5,
7
]
}
],
"properties": {
"Node name for S&R": "LoraLoaderModelOnly"
},
"widgets_values": [
"minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
1.0
]
},
{
"id": 4,
"type": "CLIPLoader",
"pos": [
40,
2392
],
"size": [
390,
300
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
2
]
}
],
"properties": {
"Node name for S&R": "CLIPLoader"
},
"widgets_values": [
"qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"minimax",
"default"
]
},
{
"id": 5,
"type": "VAELoader",
"pos": [
40,
1150
],
"size": [
390,
300
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
3,
14
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"minimax_h3_video_vae_fp16.safetensors"
]
},
{
"id": 6,
"type": "VAELoader",
"pos": [
40,
1520
],
"size": [
390,
300
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
16
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"minimax_h3_audio_vae_fp32.safetensors"
]
},
{
"id": 7,
"type": "MiniMaxH3ImageToVideo",
"pos": [
550,
1334
],
"size": [
390,
300
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 2
},
{
"name": "vae",
"type": "VAE",
"link": 3
},
{
"name": "first_frame",
"type": "IMAGE",
"link": 4
},
{
"name": "last_frame",
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"name": "positive",
"type": "CONDITIONING",
"links": [
6
]
},
{
"name": "LATENT",
"type": "LATENT",
"links": [
12
]
}
],
"properties": {
"Node name for S&R": "MiniMaxH3ImageToVideo"
},
"widgets_values": [
"For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. A tiny slow Push In toward the half-full water glass, only 3 percent over the shot. The cream fan blades rotate evenly behind its absolutely rigid grille; the fan base stays still. A soft airflow slightly lifts the translucent curtain hem and makes just the uppermost mint leaves sway with different phases. Sunlight trembles subtly through leaves onto the desk. Everything else keeps its shape. No people, no speech.\n\noverall_soundscape: Soft steady electric fan motor and a faint intermittent bearing tick, very distant daytime city ambience. No voices.\n\nnon_diegetic_music: None.",
960,
544,
124
]
},
{
"id": 8,
"type": "BasicGuider",
"pos": [
1060,
1287
],
"size": [
390,
300
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 5
},
{
"name": "conditioning",
"type": "CONDITIONING",
"link": 6
}
],
"outputs": [
{
"name": "GUIDER",
"type": "GUIDER",
"links": [
9
]
}
],
"properties": {
"Node name for S&R": "BasicGuider"
},
"widgets_values": []
},
{
"id": 9,
"type": "RandomNoise",
"pos": [
40,
410
],
"size": [
390,
300
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "NOISE",
"type": "NOISE",
"links": [
8
]
}
],
"properties": {
"Node name for S&R": "RandomNoise"
},
"widgets_values": [
246089913781214,
"fixed"
]
},
{
"id": 10,
"type": "KSamplerSelect",
"pos": [
40,
780
],
"size": [
390,
300
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "SAMPLER",
"type": "SAMPLER",
"links": [
10
]
}
],
"properties": {
"Node name for S&R": "KSamplerSelect"
},
"widgets_values": [
"res_multistep"
]
},
{
"id": 11,
"type": "BasicScheduler",
"pos": [
1060,
917
],
"size": [
390,
300
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 7
}
],
"outputs": [
{
"name": "SIGMAS",
"type": "SIGMAS",
"links": [
11
]
}
],
"properties": {
"Node name for S&R": "BasicScheduler"
},
"widgets_values": [
"simple",
8,
1.0
]
},
{
"id": 12,
"type": "SamplerCustomAdvanced",
"pos": [
1570,
1102
],
"size": [
390,
300
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "noise",
"type": "NOISE",
"link": 8
},
{
"name": "guider",
"type": "GUIDER",
"link": 9
},
{
"name": "sampler",
"type": "SAMPLER",
"link": 10
},
{
"name": "sigmas",
"type": "SIGMAS",
"link": 11
},
{
"name": "latent_image",
"type": "LATENT",
"link": 12
}
],
"outputs": [
{
"name": "output",
"type": "LATENT",
"links": [
13,
15
]
},
{
"name": "denoised_output",
"type": "LATENT",
"links": []
}
],
"properties": {
"Node name for S&R": "SamplerCustomAdvanced"
},
"widgets_values": []
},
{
"id": 13,
"type": "VAEDecode",
"pos": [
2080,
917
],
"size": [
390,
300
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 13
},
{
"name": "vae",
"type": "VAE",
"link": 14
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
17
]
}
],
"properties": {
"Node name for S&R": "VAEDecode"
},
"widgets_values": []
},
{
"id": 14,
"type": "VAEDecodeAudio",
"pos": [
2080,
1287
],
"size": [
390,
300
],
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 15
},
{
"name": "vae",
"type": "VAE",
"link": 16
}
],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
18
]
}
],
"properties": {
"Node name for S&R": "VAEDecodeAudio"
},
"widgets_values": []
},
{
"id": 15,
"type": "CreateVideo",
"pos": [
2590,
1102
],
"size": [
390,
300
],
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 17
},
{
"name": "audio",
"type": "AUDIO",
"link": 18
}
],
"outputs": [
{
"name": "VIDEO",
"type": "VIDEO",
"links": [
19
]
}
],
"properties": {
"Node name for S&R": "CreateVideo"
},
"widgets_values": [
24.0
]
},
{
"id": 16,
"type": "SaveVideo",
"pos": [
3100,
1033
],
"size": [
390,
438
],
"flags": {},
"order": 15,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": 19
}
],
"outputs": [
{
"name": "video",
"type": "VIDEO",
"links": []
}
],
"properties": {
"Node name for S&R": "SaveVideo"
},
"widgets_values": [
"hearthfire_episode/C01_V01",
"mp4",
"h264"
]
}
],
"links": [
[
1,
2,
0,
3,
0,
"MODEL"
],
[
2,
4,
0,
7,
0,
"CLIP"
],
[
3,
5,
0,
7,
1,
"VAE"
],
[
4,
1,
0,
7,
2,
"IMAGE"
],
[
5,
3,
0,
8,
0,
"MODEL"
],
[
6,
7,
0,
8,
1,
"CONDITIONING"
],
[
7,
3,
0,
11,
0,
"MODEL"
],
[
8,
9,
0,
12,
0,
"NOISE"
],
[
9,
8,
0,
12,
1,
"GUIDER"
],
[
10,
10,
0,
12,
2,
"SAMPLER"
],
[
11,
11,
0,
12,
3,
"SIGMAS"
],
[
12,
7,
1,
12,
4,
"LATENT"
],
[
13,
12,
0,
13,
0,
"LATENT"
],
[
14,
5,
0,
13,
1,
"VAE"
],
[
15,
12,
0,
14,
0,
"LATENT"
],
[
16,
6,
0,
14,
1,
"VAE"
],
[
17,
13,
0,
15,
0,
"IMAGE"
],
[
18,
14,
0,
15,
1,
"AUDIO"
],
[
19,
15,
0,
16,
0,
"VIDEO"
]
],
"groups": [
{
"title": "EP01 full episode - MiniMax H3 - native audio",
"bounding": [
-5,
-51,
3540,
2788
],
"color": "#335159",
"font_size": 24
}
],
"config": {},
"extra": {},
"version": 0.4
}
@@ -0,0 +1,57 @@
{
"file": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C01\\C01_V01_00001_.mp4",
"format": "mov,mp4,m4a,3gp,3g2,mj2",
"duration": 5.167,
"size_bytes": 1366467,
"bitrate": 2115683,
"video": {
"codec": "h264",
"profile": "High",
"width": 960,
"height": 544,
"display_aspect": "30:17",
"fps": 24.0,
"r_frame_rate": "24/1",
"avg_frame_rate": "24/1",
"variable_frame_rate_suspected": false,
"pix_fmt": "yuv420p",
"bit_depth": 8,
"hdr": false,
"hdr_signal": false,
"bt2020_or_hdr": false,
"hdr_format": null,
"dolby_vision": null,
"color_space": "bt709",
"color_primaries": "bt709",
"color_transfer": "iec61966-2-1",
"color_range": "tv",
"rotation": 0,
"nb_frames": 124,
"duration": 5.166667,
"bitrate": 1962247
},
"audio": {
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"bitrate": 127310,
"duration": 5.167
},
"subtitle_streams": 0,
"data_streams": 0,
"chapters": [],
"tags": {},
"subtitle_stream_details": [],
"audio_streams": [
{
"index": 0,
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"language": "und",
"title": null
}
]
}
@@ -0,0 +1,18 @@
{
"prompt_id": "045d5dfd-9071-4a0a-affc-3ca27ba2e9f9",
"number": 96,
"node_errors": {},
"seed": 261268034150927,
"frames": 158,
"width": 960,
"height": 544,
"submitted_at": 1790658547.7807293,
"shot": {
"id": "C02",
"image": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\frames\\C02.png",
"seconds": 6,
"edit_seconds": 6,
"prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Locked over-left-shoulder shot. The orange cat on the monitor is a completely motionless photograph. The man leans forward by one centimeter, his eyes scan from the cat to its result, pauses in mild disbelief, then at 00:01.400 says softly <d>[Chinese] 锅。</d> (S1: adult 29-year-old male, warm medium-low natural Mandarin voice, dry understated humor, conversational not declamatory.) A short thoughtful beat follows. At 00:03.200 his index finger depresses and releases the mouse once. Shoulders relax, only a small exhale. Keep monitor geometry fixed. The right results panel stays blank and unchanged, added in post. No animals physically enter the room.\n\noverall_soundscape: Same quiet fan bearing hum, one dry mouse click, the one short spoken word only.\n\nnon_diegetic_music: None.",
"dialogue": "锅。"
}
}
@@ -0,0 +1,13 @@
{
"summary": "nodes=16 edges=19 overlaps=0 crossings=9 bounds=[40, 40, 3490, 2692]",
"overlaps": [],
"crossings": 9,
"bounds": [
40.0,
40.0,
3490.0,
2692.0
],
"n_nodes": 16,
"n_edges": 19
}
@@ -0,0 +1,3 @@
[
"F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\C02_V01_00001_.mp4"
]
@@ -0,0 +1,85 @@
{
"status": "completed",
"output": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen.mp4",
"dry_run": false,
"commands": [
"'C:/Users/zhang/.codex/tools/media-bin\\ffmpeg.EXE' -hide_banner -loglevel error -nostdin -y -i 'F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen_silent.mp4' -i 'F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\C02_V01_00001_.mp4' -filter_complex '[1:a:0]anull[main];[main]apad,atrim=0:6.583[out]' -map '[out]' -map 0:v:0 -c:v copy -movflags +faststart -c:a aac -b:a 192k -map '0:s?' -map '0:d?' -c:s copy -c:d copy 'F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen.mp4'"
],
"probe": {
"file": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen.mp4",
"format": "mov,mp4,m4a,3gp,3g2,mj2",
"duration": 6.583333,
"size_bytes": 1397187,
"bitrate": 1697847,
"video": {
"codec": "h264",
"profile": "High",
"width": 960,
"height": 544,
"display_aspect": "30:17",
"fps": 24.0,
"r_frame_rate": "24/1",
"avg_frame_rate": "24/1",
"variable_frame_rate_suspected": false,
"pix_fmt": "yuv420p",
"bit_depth": 8,
"hdr": false,
"hdr_signal": false,
"bt2020_or_hdr": false,
"hdr_format": null,
"dolby_vision": null,
"color_space": "bt709",
"color_primaries": null,
"color_transfer": null,
"color_range": "tv",
"rotation": 0,
"nb_frames": 158,
"duration": 6.583333,
"bitrate": 1520550
},
"audio": {
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"bitrate": 168526,
"duration": 6.583
},
"subtitle_streams": 0,
"data_streams": 0,
"chapters": [],
"tags": {},
"subtitle_stream_details": [],
"audio_streams": [
{
"index": 0,
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"language": "und",
"title": null
}
]
},
"verified": true,
"verification": [
{
"step": "probe",
"ok": true
}
],
"audio": {
"voice": null,
"stereo_widen": null,
"effects": false,
"effects_volume": null
},
"video": true,
"audio_stream": 0,
"dynamics": [],
"dropped_non_av_streams": false
}
$ 'C:/Users/zhang/.codex/tools/media-bin\ffmpeg.EXE' -hide_banner -loglevel error -nostdin -y -i 'F:\project\小说设计\06_AI动漫制作\05_生产素材\视频测试\2026-09-29_H3_开篇40秒_柔光V02\C02\post_screen_silent.mp4' -i 'F:\project\小说设计\06_AI动漫制作\05_生产素材\视频测试\2026-09-29_H3_开篇40秒_柔光V02\C02\C02_V01_00001_.mp4' -filter_complex '[1:a:0]anull[main];[main]apad,atrim=0:6.583[out]' -map '[out]' -map 0:v:0 -c:v copy -movflags +faststart -c:a aac -b:a 192k -map '0:s?' -map '0:d?' -c:s copy -c:d copy 'F:\project\小说设计\06_AI动漫制作\05_生产素材\视频测试\2026-09-29_H3_开篇40秒_柔光V02\C02\post_screen.mp4'
wrote F:\project\小说设计\06_AI动漫制作\05_生产素材\视频测试\2026-09-29_H3_开篇40秒_柔光V02\C02\post_screen.mp4 (6.583s, audio aac 2ch 32000Hz, video stream-copied)
@@ -0,0 +1,23 @@
{
"status": "completed",
"output": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen.mp4",
"dry_run": true,
"commands": [
"'C:/Users/zhang/.codex/tools/media-bin\\ffmpeg.EXE' -hide_banner -loglevel error -nostdin -y -i 'F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen_silent.mp4' -i 'F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\C02_V01_00001_.mp4' -filter_complex '[1:a:0]anull[main];[main]apad,atrim=0:6.583[out]' -map '[out]' -map 0:v:0 -c:v copy -movflags +faststart -c:a aac -b:a 192k -map '0:s?' -map '0:d?' -c:s copy -c:d copy 'F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen.mp4'"
],
"verified": false,
"verification": [],
"audio": {
"voice": null,
"stereo_widen": null,
"effects": false,
"effects_volume": null
},
"video": true,
"audio_stream": 0,
"dynamics": [],
"dropped_non_av_streams": false
}
[dry-run] $ 'C:/Users/zhang/.codex/tools/media-bin\ffmpeg.EXE' -hide_banner -loglevel error -nostdin -y -i 'F:\project\小说设计\06_AI动漫制作\05_生产素材\视频测试\2026-09-29_H3_开篇40秒_柔光V02\C02\post_screen_silent.mp4' -i 'F:\project\小说设计\06_AI动漫制作\05_生产素材\视频测试\2026-09-29_H3_开篇40秒_柔光V02\C02\C02_V01_00001_.mp4' -filter_complex '[1:a:0]anull[main];[main]apad,atrim=0:6.583[out]' -map '[out]' -map 0:v:0 -c:v copy -movflags +faststart -c:a aac -b:a 192k -map '0:s?' -map '0:d?' -c:s copy -c:d copy 'F:\project\小说设计\06_AI动漫制作\05_生产素材\视频测试\2026-09-29_H3_开篇40秒_柔光V02\C02\post_screen.mp4'
[dry-run] would write F:\project\小说设计\06_AI动漫制作\05_生产素材\视频测试\2026-09-29_H3_开篇40秒_柔光V02\C02\post_screen.mp4 (0.000s, audio None 0ch 0Hz, video stream-copied)
@@ -0,0 +1,77 @@
{
"status": "completed",
"output": null,
"dry_run": false,
"commands": [],
"verified": false,
"verification": [],
"platform": "custom",
"checks": [
{
"check": "duration",
"status": "PASS",
"value": "6.58s",
"expected": "any",
"fix": "",
"reason": "",
"kind": "judgement"
},
{
"check": "aspect",
"status": "PASS",
"value": "16:9",
"expected": "any",
"fix": "",
"reason": "",
"kind": "judgement"
},
{
"check": "vfr",
"status": "PASS",
"value": "constant",
"expected": "constant",
"fix": "fit.py --fps N (any re-encode conforms it)",
"reason": "",
"kind": "format"
},
{
"check": "colour",
"status": "PASS",
"value": "None/None",
"expected": "bt709/bt709 tagged (or HDR)",
"fix": "",
"reason": "",
"kind": "format"
},
{
"check": "audio",
"status": "PASS",
"value": "aac 2ch 32000Hz",
"expected": "present",
"fix": "",
"reason": "",
"kind": "format"
},
{
"check": "subtitles",
"status": "WARN",
"value": "none",
"expected": ">= 1 language-tagged subtitle track",
"fix": "caption.py video.mp4 --mode mux --srt subs.srt:en -o video_subs.mkv (streams are copied)",
"reason": "subtitles are optional, but they are the cheapest accessibility win a delivery has",
"kind": "format"
},
{
"check": "sample rate",
"status": "WARN",
"value": 32000,
"expected": "44100 or 48000",
"fix": "loudness.py --sample-rate 48000",
"reason": "",
"kind": "format"
}
],
"failed": 0,
"warnings": 2,
"ok": true
}
@@ -0,0 +1,3 @@
[
"F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen.mp4"
]
@@ -0,0 +1,14 @@
{
"status": "completed",
"output": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen_silent.mp4",
"dry_run": true,
"commands": [
"'C:/Users/zhang/.codex/tools/media-bin\\ffmpeg.EXE' -hide_banner -loglevel error -nostdin -y -f concat -safe 0 -i 'C:\\Users\\zhang\\AppData\\Local\\Temp\\ffmpeg-skill-sequence-asqud1m1\\frames.txt' -vf scale=960:544,setsar=1,fps=24 -c:v libx264 -preset medium -crf 18 -pix_fmt yuv420p -movflags +faststart -colorspace bt709 -color_primaries bt709 -color_trc bt709 -t 6.583333 -an 'F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen_silent.mp4'"
],
"verified": false,
"verification": []
}
found 158 consecutive frames from index 0
[dry-run] $ 'C:/Users/zhang/.codex/tools/media-bin\ffmpeg.EXE' -hide_banner -loglevel error -nostdin -y -f concat -safe 0 -i 'C:\Users\zhang\AppData\Local\Temp\ffmpeg-skill-sequence-asqud1m1\frames.txt' -vf scale=960:544,setsar=1,fps=24 -c:v libx264 -preset medium -crf 18 -pix_fmt yuv420p -movflags +faststart -colorspace bt709 -color_primaries bt709 -color_trc bt709 -t 6.583333 -an 'F:\project\小说设计\06_AI动漫制作\05_生产素材\视频测试\2026-09-29_H3_开篇40秒_柔光V02\C02\post_screen_silent.mp4'
[dry-run] would write F:\project\小说设计\06_AI动漫制作\05_生产素材\视频测试\2026-09-29_H3_开篇40秒_柔光V02\C02\post_screen_silent.mp4 (0.000s, 0x0, 0fps)
@@ -0,0 +1,57 @@
{
"file": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen.mp4",
"format": "mov,mp4,m4a,3gp,3g2,mj2",
"duration": 6.583333,
"size_bytes": 1397187,
"bitrate": 1697847,
"video": {
"codec": "h264",
"profile": "High",
"width": 960,
"height": 544,
"display_aspect": "30:17",
"fps": 24.0,
"r_frame_rate": "24/1",
"avg_frame_rate": "24/1",
"variable_frame_rate_suspected": false,
"pix_fmt": "yuv420p",
"bit_depth": 8,
"hdr": false,
"hdr_signal": false,
"bt2020_or_hdr": false,
"hdr_format": null,
"dolby_vision": null,
"color_space": "bt709",
"color_primaries": null,
"color_transfer": null,
"color_range": "tv",
"rotation": 0,
"nb_frames": 158,
"duration": 6.583333,
"bitrate": 1520550
},
"audio": {
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"bitrate": 168526,
"duration": 6.583
},
"subtitle_streams": 0,
"data_streams": 0,
"chapters": [],
"tags": {},
"subtitle_stream_details": [],
"audio_streams": [
{
"index": 0,
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"language": "und",
"title": null
}
]
}
Binary file not shown.

After

Width:  |  Height:  |  Size: 1.1 MiB

@@ -0,0 +1,58 @@
{
"status": "completed",
"output": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen_silent.mp4",
"dry_run": false,
"commands": [
"'C:/Users/zhang/.codex/tools/media-bin\\ffmpeg.EXE' -hide_banner -loglevel error -nostdin -y -f concat -safe 0 -i 'C:\\Users\\zhang\\AppData\\Local\\Temp\\ffmpeg-skill-sequence-59jm1ahf\\frames.txt' -vf scale=960:544,setsar=1,fps=24 -c:v libx264 -preset medium -crf 18 -pix_fmt yuv420p -movflags +faststart -colorspace bt709 -color_primaries bt709 -color_trc bt709 -t 6.583333 -an 'F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen_silent.mp4'"
],
"probe": {
"file": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen_silent.mp4",
"format": "mov,mp4,m4a,3gp,3g2,mj2",
"duration": 6.583333,
"size_bytes": 1254068,
"bitrate": 1523930,
"video": {
"codec": "h264",
"profile": "High",
"width": 960,
"height": 544,
"display_aspect": "30:17",
"fps": 24.0,
"r_frame_rate": "24/1",
"avg_frame_rate": "24/1",
"variable_frame_rate_suspected": false,
"pix_fmt": "yuv420p",
"bit_depth": 8,
"hdr": false,
"hdr_signal": false,
"bt2020_or_hdr": false,
"hdr_format": null,
"dolby_vision": null,
"color_space": "bt709",
"color_primaries": null,
"color_transfer": null,
"color_range": "tv",
"rotation": 0,
"nb_frames": 158,
"duration": 6.583333,
"bitrate": 1520550
},
"audio": null,
"subtitle_streams": 0,
"data_streams": 0,
"chapters": [],
"tags": {},
"subtitle_stream_details": []
},
"verified": true,
"verification": [
{
"step": "probe",
"ok": true
}
]
}
found 158 consecutive frames from index 0
$ 'C:/Users/zhang/.codex/tools/media-bin\ffmpeg.EXE' -hide_banner -loglevel error -nostdin -y -f concat -safe 0 -i 'C:\Users\zhang\AppData\Local\Temp\ffmpeg-skill-sequence-59jm1ahf\frames.txt' -vf scale=960:544,setsar=1,fps=24 -c:v libx264 -preset medium -crf 18 -pix_fmt yuv420p -movflags +faststart -colorspace bt709 -color_primaries bt709 -color_trc bt709 -t 6.583333 -an 'F:\project\小说设计\06_AI动漫制作\05_生产素材\视频测试\2026-09-29_H3_开篇40秒_柔光V02\C02\post_screen_silent.mp4'
wrote F:\project\小说设计\06_AI动漫制作\05_生产素材\视频测试\2026-09-29_H3_开篇40秒_柔光V02\C02\post_screen_silent.mp4 (6.583s, 960x544, 24fps)
@@ -0,0 +1,7 @@
For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
integrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Locked over-left-shoulder shot. The orange cat on the monitor is a completely motionless photograph. The man leans forward by one centimeter, his eyes scan from the cat to its result, pauses in mild disbelief, then at 00:01.400 says softly <d>[Chinese] 锅。</d> (S1: adult 29-year-old male, warm medium-low natural Mandarin voice, dry understated humor, conversational not declamatory.) A short thoughtful beat follows. At 00:03.200 his index finger depresses and releases the mouse once. Shoulders relax, only a small exhale. Keep monitor geometry fixed. The right results panel stays blank and unchanged, added in post. No animals physically enter the room.
overall_soundscape: Same quiet fan bearing hum, one dry mouse click, the one short spoken word only.
non_diegetic_music: None.
Binary file not shown.

After

Width:  |  Height:  |  Size: 1.1 MiB

@@ -0,0 +1,64 @@
{
"shot": "C02",
"coordinate_space": {
"width": 1672,
"height": 941
},
"screen_quad_clockwise": [
[
1007,
247
],
[
1634,
222
],
[
1618,
665
],
[
988,
600
]
],
"panel_quad_clockwise": [
[
1283,
267
],
[
1612,
256
],
[
1599,
624
],
[
1269,
594
]
],
"track": "Planar track screen after H3; these are first-frame anchors, do not assume every generated frame identical.",
"events": [
{
"start": 0,
"end": 6,
"text": "分类结果:锅",
"style": "dark charcoal simplified Chinese, centered within result panel"
},
{
"start": 0,
"end": 2.6,
"text": "✓",
"style": "small green check below result"
},
{
"start": 2.6,
"end": 6,
"text": "×",
"style": "thin red strike through check; generated as postproduction overlay"
}
]
}
@@ -0,0 +1,12 @@
{
"expected": "锅。",
"recognized": "哭",
"segments": [
{
"start": 1.01,
"end": 2.01,
"text": "哭"
}
],
"note": "ASR transcription, not a listening certification."
}
@@ -0,0 +1,5 @@
{
"prompt_id": "045d5dfd-9071-4a0a-affc-3ca27ba2e9f9",
"number": 96,
"node_errors": {}
}
@@ -0,0 +1,181 @@
{
"1": {
"class_type": "LoadImage",
"inputs": {
"image": "hearthfire_h3/C02_C02.png"
}
},
"2": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"weight_dtype": "default"
}
},
"3": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"model": [
"2",
0
],
"lora_name": "minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
"strength_model": 1.0
}
},
"4": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"type": "minimax",
"device": "default"
}
},
"5": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "minimax_h3_video_vae_fp16.safetensors"
}
},
"6": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "minimax_h3_audio_vae_fp32.safetensors"
}
},
"7": {
"class_type": "MiniMaxH3ImageToVideo",
"inputs": {
"clip": [
"4",
0
],
"vae": [
"5",
0
],
"first_frame": [
"1",
0
],
"prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Locked over-left-shoulder shot. The orange cat on the monitor is a completely motionless photograph. The man leans forward by one centimeter, his eyes scan from the cat to its result, pauses in mild disbelief, then at 00:01.400 says softly <d>[Chinese] 锅。</d> (S1: adult 29-year-old male, warm medium-low natural Mandarin voice, dry understated humor, conversational not declamatory.) A short thoughtful beat follows. At 00:03.200 his index finger depresses and releases the mouse once. Shoulders relax, only a small exhale. Keep monitor geometry fixed. The right results panel stays blank and unchanged, added in post. No animals physically enter the room.\n\noverall_soundscape: Same quiet fan bearing hum, one dry mouse click, the one short spoken word only.\n\nnon_diegetic_music: None.",
"width": 960,
"height": 544,
"length": 158
}
},
"8": {
"class_type": "BasicGuider",
"inputs": {
"model": [
"3",
0
],
"conditioning": [
"7",
0
]
}
},
"9": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 261268034150927
}
},
"10": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "res_multistep"
}
},
"11": {
"class_type": "BasicScheduler",
"inputs": {
"model": [
"3",
0
],
"scheduler": "simple",
"steps": 8,
"denoise": 1.0
}
},
"12": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"noise": [
"9",
0
],
"guider": [
"8",
0
],
"sampler": [
"10",
0
],
"sigmas": [
"11",
0
],
"latent_image": [
"7",
1
]
}
},
"13": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"12",
0
],
"vae": [
"5",
0
]
}
},
"14": {
"class_type": "VAEDecodeAudio",
"inputs": {
"samples": [
"12",
0
],
"vae": [
"6",
0
]
}
},
"15": {
"class_type": "CreateVideo",
"inputs": {
"images": [
"13",
0
],
"audio": [
"14",
0
],
"fps": 24.0
}
},
"16": {
"class_type": "SaveVideo",
"inputs": {
"video": [
"15",
0
],
"filename_prefix": "hearthfire_episode/C02_V01",
"format": "mp4",
"codec": "h264"
}
}
}
@@ -0,0 +1,804 @@
{
"last_node_id": 16,
"last_link_id": 19,
"nodes": [
{
"id": 1,
"type": "LoadImage",
"pos": [
40,
1890
],
"size": [
390,
432
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
4
]
},
{
"name": "MASK",
"type": "MASK",
"links": []
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"hearthfire_h3/C02_C02.png",
"image"
]
},
{
"id": 2,
"type": "UNETLoader",
"pos": [
40,
40
],
"size": [
390,
300
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
1
]
}
],
"properties": {
"Node name for S&R": "UNETLoader"
},
"widgets_values": [
"minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"default"
]
},
{
"id": 3,
"type": "LoraLoaderModelOnly",
"pos": [
550,
964
],
"size": [
390,
300
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 1
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
5,
7
]
}
],
"properties": {
"Node name for S&R": "LoraLoaderModelOnly"
},
"widgets_values": [
"minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
1.0
]
},
{
"id": 4,
"type": "CLIPLoader",
"pos": [
40,
2392
],
"size": [
390,
300
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
2
]
}
],
"properties": {
"Node name for S&R": "CLIPLoader"
},
"widgets_values": [
"qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"minimax",
"default"
]
},
{
"id": 5,
"type": "VAELoader",
"pos": [
40,
1150
],
"size": [
390,
300
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
3,
14
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"minimax_h3_video_vae_fp16.safetensors"
]
},
{
"id": 6,
"type": "VAELoader",
"pos": [
40,
1520
],
"size": [
390,
300
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
16
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"minimax_h3_audio_vae_fp32.safetensors"
]
},
{
"id": 7,
"type": "MiniMaxH3ImageToVideo",
"pos": [
550,
1334
],
"size": [
390,
300
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 2
},
{
"name": "vae",
"type": "VAE",
"link": 3
},
{
"name": "first_frame",
"type": "IMAGE",
"link": 4
},
{
"name": "last_frame",
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"name": "positive",
"type": "CONDITIONING",
"links": [
6
]
},
{
"name": "LATENT",
"type": "LATENT",
"links": [
12
]
}
],
"properties": {
"Node name for S&R": "MiniMaxH3ImageToVideo"
},
"widgets_values": [
"For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Locked over-left-shoulder shot. The orange cat on the monitor is a completely motionless photograph. The man leans forward by one centimeter, his eyes scan from the cat to its result, pauses in mild disbelief, then at 00:01.400 says softly <d>[Chinese] 锅。</d> (S1: adult 29-year-old male, warm medium-low natural Mandarin voice, dry understated humor, conversational not declamatory.) A short thoughtful beat follows. At 00:03.200 his index finger depresses and releases the mouse once. Shoulders relax, only a small exhale. Keep monitor geometry fixed. The right results panel stays blank and unchanged, added in post. No animals physically enter the room.\n\noverall_soundscape: Same quiet fan bearing hum, one dry mouse click, the one short spoken word only.\n\nnon_diegetic_music: None.",
960,
544,
158
]
},
{
"id": 8,
"type": "BasicGuider",
"pos": [
1060,
1287
],
"size": [
390,
300
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 5
},
{
"name": "conditioning",
"type": "CONDITIONING",
"link": 6
}
],
"outputs": [
{
"name": "GUIDER",
"type": "GUIDER",
"links": [
9
]
}
],
"properties": {
"Node name for S&R": "BasicGuider"
},
"widgets_values": []
},
{
"id": 9,
"type": "RandomNoise",
"pos": [
40,
410
],
"size": [
390,
300
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "NOISE",
"type": "NOISE",
"links": [
8
]
}
],
"properties": {
"Node name for S&R": "RandomNoise"
},
"widgets_values": [
261268034150927,
"fixed"
]
},
{
"id": 10,
"type": "KSamplerSelect",
"pos": [
40,
780
],
"size": [
390,
300
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "SAMPLER",
"type": "SAMPLER",
"links": [
10
]
}
],
"properties": {
"Node name for S&R": "KSamplerSelect"
},
"widgets_values": [
"res_multistep"
]
},
{
"id": 11,
"type": "BasicScheduler",
"pos": [
1060,
917
],
"size": [
390,
300
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 7
}
],
"outputs": [
{
"name": "SIGMAS",
"type": "SIGMAS",
"links": [
11
]
}
],
"properties": {
"Node name for S&R": "BasicScheduler"
},
"widgets_values": [
"simple",
8,
1.0
]
},
{
"id": 12,
"type": "SamplerCustomAdvanced",
"pos": [
1570,
1102
],
"size": [
390,
300
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "noise",
"type": "NOISE",
"link": 8
},
{
"name": "guider",
"type": "GUIDER",
"link": 9
},
{
"name": "sampler",
"type": "SAMPLER",
"link": 10
},
{
"name": "sigmas",
"type": "SIGMAS",
"link": 11
},
{
"name": "latent_image",
"type": "LATENT",
"link": 12
}
],
"outputs": [
{
"name": "output",
"type": "LATENT",
"links": [
13,
15
]
},
{
"name": "denoised_output",
"type": "LATENT",
"links": []
}
],
"properties": {
"Node name for S&R": "SamplerCustomAdvanced"
},
"widgets_values": []
},
{
"id": 13,
"type": "VAEDecode",
"pos": [
2080,
917
],
"size": [
390,
300
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 13
},
{
"name": "vae",
"type": "VAE",
"link": 14
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
17
]
}
],
"properties": {
"Node name for S&R": "VAEDecode"
},
"widgets_values": []
},
{
"id": 14,
"type": "VAEDecodeAudio",
"pos": [
2080,
1287
],
"size": [
390,
300
],
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 15
},
{
"name": "vae",
"type": "VAE",
"link": 16
}
],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
18
]
}
],
"properties": {
"Node name for S&R": "VAEDecodeAudio"
},
"widgets_values": []
},
{
"id": 15,
"type": "CreateVideo",
"pos": [
2590,
1102
],
"size": [
390,
300
],
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 17
},
{
"name": "audio",
"type": "AUDIO",
"link": 18
}
],
"outputs": [
{
"name": "VIDEO",
"type": "VIDEO",
"links": [
19
]
}
],
"properties": {
"Node name for S&R": "CreateVideo"
},
"widgets_values": [
24.0
]
},
{
"id": 16,
"type": "SaveVideo",
"pos": [
3100,
1033
],
"size": [
390,
438
],
"flags": {},
"order": 15,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": 19
}
],
"outputs": [
{
"name": "video",
"type": "VIDEO",
"links": []
}
],
"properties": {
"Node name for S&R": "SaveVideo"
},
"widgets_values": [
"hearthfire_episode/C02_V01",
"mp4",
"h264"
]
}
],
"links": [
[
1,
2,
0,
3,
0,
"MODEL"
],
[
2,
4,
0,
7,
0,
"CLIP"
],
[
3,
5,
0,
7,
1,
"VAE"
],
[
4,
1,
0,
7,
2,
"IMAGE"
],
[
5,
3,
0,
8,
0,
"MODEL"
],
[
6,
7,
0,
8,
1,
"CONDITIONING"
],
[
7,
3,
0,
11,
0,
"MODEL"
],
[
8,
9,
0,
12,
0,
"NOISE"
],
[
9,
8,
0,
12,
1,
"GUIDER"
],
[
10,
10,
0,
12,
2,
"SAMPLER"
],
[
11,
11,
0,
12,
3,
"SIGMAS"
],
[
12,
7,
1,
12,
4,
"LATENT"
],
[
13,
12,
0,
13,
0,
"LATENT"
],
[
14,
5,
0,
13,
1,
"VAE"
],
[
15,
12,
0,
14,
0,
"LATENT"
],
[
16,
6,
0,
14,
1,
"VAE"
],
[
17,
13,
0,
15,
0,
"IMAGE"
],
[
18,
14,
0,
15,
1,
"AUDIO"
],
[
19,
15,
0,
16,
0,
"VIDEO"
]
],
"groups": [
{
"title": "EP01 full episode - MiniMax H3 - native audio",
"bounding": [
-5,
-51,
3540,
2788
],
"color": "#335159",
"font_size": 24
}
],
"config": {},
"extra": {},
"version": 0.4
}
@@ -0,0 +1,57 @@
{
"file": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C02\\post_screen.mp4",
"format": "mov,mp4,m4a,3gp,3g2,mj2",
"duration": 6.583333,
"size_bytes": 1397187,
"bitrate": 1697847,
"video": {
"codec": "h264",
"profile": "High",
"width": 960,
"height": 544,
"display_aspect": "30:17",
"fps": 24.0,
"r_frame_rate": "24/1",
"avg_frame_rate": "24/1",
"variable_frame_rate_suspected": false,
"pix_fmt": "yuv420p",
"bit_depth": 8,
"hdr": false,
"hdr_signal": false,
"bt2020_or_hdr": false,
"hdr_format": null,
"dolby_vision": null,
"color_space": "bt709",
"color_primaries": null,
"color_transfer": null,
"color_range": "tv",
"rotation": 0,
"nb_frames": 158,
"duration": 6.583333,
"bitrate": 1520550
},
"audio": {
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"bitrate": 168526,
"duration": 6.583
},
"subtitle_streams": 0,
"data_streams": 0,
"chapters": [],
"tags": {},
"subtitle_stream_details": [],
"audio_streams": [
{
"index": 0,
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"language": "und",
"title": null
}
]
}
@@ -0,0 +1,18 @@
{
"prompt_id": "503e2583-19b2-4a48-8f67-14e5aaa44caa",
"number": 94,
"node_errors": {},
"seed": 86764637570136,
"frames": 158,
"width": 960,
"height": 544,
"submitted_at": 1790658181.790821,
"shot": {
"id": "C03",
"image": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\frames\\C03.png",
"seconds": 6,
"edit_seconds": 6,
"prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Medium close side profile. A small slow Push In, just 2 percent. Eyes remain on the computer at screen right. At 00:00.500 the man (S1: adult 29-year-old male, warm medium-low natural Mandarin voice, relaxed conversational rhythm and dry understated humor) quietly says <d>[Chinese] 今天还挺有主见。</d> The phrase ends before 00:03.300. Start with a tiny amused exhale, lips and jaw articulate naturally while cheeks remain relaxed. A barely visible smile briefly lifts one corner of the mouth. At 00:03.800 he blinks once, lets the smile soften and lowers his gaze toward his notes. Breathing causes a very small irregular shoulder shift. No large head turn. No animals or new objects appear.\n\noverall_soundscape: Soft electric fan hum, the exact one Mandarin sentence close and intimate, a quiet breath afterward. No additional voices.\n\nnon_diegetic_music: None.",
"dialogue": "今天还挺有主见。"
}
}
@@ -0,0 +1,13 @@
{
"summary": "nodes=16 edges=19 overlaps=0 crossings=9 bounds=[40, 40, 3490, 2692]",
"overlaps": [],
"crossings": 9,
"bounds": [
40.0,
40.0,
3490.0,
2692.0
],
"n_nodes": 16,
"n_edges": 19
}
@@ -0,0 +1,3 @@
[
"F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C03\\C03_V01_00001_.mp4"
]
@@ -0,0 +1,7 @@
For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
integrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Medium close side profile. A small slow Push In, just 2 percent. Eyes remain on the computer at screen right. At 00:00.500 the man (S1: adult 29-year-old male, warm medium-low natural Mandarin voice, relaxed conversational rhythm and dry understated humor) quietly says <d>[Chinese] 今天还挺有主见。</d> The phrase ends before 00:03.300. Start with a tiny amused exhale, lips and jaw articulate naturally while cheeks remain relaxed. A barely visible smile briefly lifts one corner of the mouth. At 00:03.800 he blinks once, lets the smile soften and lowers his gaze toward his notes. Breathing causes a very small irregular shoulder shift. No large head turn. No animals or new objects appear.
overall_soundscape: Soft electric fan hum, the exact one Mandarin sentence close and intimate, a quiet breath afterward. No additional voices.
non_diegetic_music: None.
Binary file not shown.

After

Width:  |  Height:  |  Size: 1.2 MiB

@@ -0,0 +1,12 @@
{
"expected": "今天还挺有主见。",
"recognized": "今天还挺有主见",
"segments": [
{
"start": 2.29,
"end": 4.29,
"text": "今天还挺有主见"
}
],
"note": "ASR transcription, not a listening certification."
}
@@ -0,0 +1,5 @@
{
"prompt_id": "503e2583-19b2-4a48-8f67-14e5aaa44caa",
"number": 94,
"node_errors": {}
}
@@ -0,0 +1,181 @@
{
"1": {
"class_type": "LoadImage",
"inputs": {
"image": "hearthfire_h3/C03_C03.png"
}
},
"2": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"weight_dtype": "default"
}
},
"3": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"model": [
"2",
0
],
"lora_name": "minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
"strength_model": 1.0
}
},
"4": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"type": "minimax",
"device": "default"
}
},
"5": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "minimax_h3_video_vae_fp16.safetensors"
}
},
"6": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "minimax_h3_audio_vae_fp32.safetensors"
}
},
"7": {
"class_type": "MiniMaxH3ImageToVideo",
"inputs": {
"clip": [
"4",
0
],
"vae": [
"5",
0
],
"first_frame": [
"1",
0
],
"prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Medium close side profile. A small slow Push In, just 2 percent. Eyes remain on the computer at screen right. At 00:00.500 the man (S1: adult 29-year-old male, warm medium-low natural Mandarin voice, relaxed conversational rhythm and dry understated humor) quietly says <d>[Chinese] 今天还挺有主见。</d> The phrase ends before 00:03.300. Start with a tiny amused exhale, lips and jaw articulate naturally while cheeks remain relaxed. A barely visible smile briefly lifts one corner of the mouth. At 00:03.800 he blinks once, lets the smile soften and lowers his gaze toward his notes. Breathing causes a very small irregular shoulder shift. No large head turn. No animals or new objects appear.\n\noverall_soundscape: Soft electric fan hum, the exact one Mandarin sentence close and intimate, a quiet breath afterward. No additional voices.\n\nnon_diegetic_music: None.",
"width": 960,
"height": 544,
"length": 158
}
},
"8": {
"class_type": "BasicGuider",
"inputs": {
"model": [
"3",
0
],
"conditioning": [
"7",
0
]
}
},
"9": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 86764637570136
}
},
"10": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "res_multistep"
}
},
"11": {
"class_type": "BasicScheduler",
"inputs": {
"model": [
"3",
0
],
"scheduler": "simple",
"steps": 8,
"denoise": 1.0
}
},
"12": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"noise": [
"9",
0
],
"guider": [
"8",
0
],
"sampler": [
"10",
0
],
"sigmas": [
"11",
0
],
"latent_image": [
"7",
1
]
}
},
"13": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"12",
0
],
"vae": [
"5",
0
]
}
},
"14": {
"class_type": "VAEDecodeAudio",
"inputs": {
"samples": [
"12",
0
],
"vae": [
"6",
0
]
}
},
"15": {
"class_type": "CreateVideo",
"inputs": {
"images": [
"13",
0
],
"audio": [
"14",
0
],
"fps": 24.0
}
},
"16": {
"class_type": "SaveVideo",
"inputs": {
"video": [
"15",
0
],
"filename_prefix": "hearthfire_episode/C03_V01",
"format": "mp4",
"codec": "h264"
}
}
}
@@ -0,0 +1,804 @@
{
"last_node_id": 16,
"last_link_id": 19,
"nodes": [
{
"id": 1,
"type": "LoadImage",
"pos": [
40,
1890
],
"size": [
390,
432
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
4
]
},
{
"name": "MASK",
"type": "MASK",
"links": []
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"hearthfire_h3/C03_C03.png",
"image"
]
},
{
"id": 2,
"type": "UNETLoader",
"pos": [
40,
40
],
"size": [
390,
300
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
1
]
}
],
"properties": {
"Node name for S&R": "UNETLoader"
},
"widgets_values": [
"minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"default"
]
},
{
"id": 3,
"type": "LoraLoaderModelOnly",
"pos": [
550,
964
],
"size": [
390,
300
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 1
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
5,
7
]
}
],
"properties": {
"Node name for S&R": "LoraLoaderModelOnly"
},
"widgets_values": [
"minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
1.0
]
},
{
"id": 4,
"type": "CLIPLoader",
"pos": [
40,
2392
],
"size": [
390,
300
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
2
]
}
],
"properties": {
"Node name for S&R": "CLIPLoader"
},
"widgets_values": [
"qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"minimax",
"default"
]
},
{
"id": 5,
"type": "VAELoader",
"pos": [
40,
1150
],
"size": [
390,
300
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
3,
14
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"minimax_h3_video_vae_fp16.safetensors"
]
},
{
"id": 6,
"type": "VAELoader",
"pos": [
40,
1520
],
"size": [
390,
300
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
16
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"minimax_h3_audio_vae_fp32.safetensors"
]
},
{
"id": 7,
"type": "MiniMaxH3ImageToVideo",
"pos": [
550,
1334
],
"size": [
390,
300
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 2
},
{
"name": "vae",
"type": "VAE",
"link": 3
},
{
"name": "first_frame",
"type": "IMAGE",
"link": 4
},
{
"name": "last_frame",
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"name": "positive",
"type": "CONDITIONING",
"links": [
6
]
},
{
"name": "LATENT",
"type": "LATENT",
"links": [
12
]
}
],
"properties": {
"Node name for S&R": "MiniMaxH3ImageToVideo"
},
"widgets_values": [
"For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Medium close side profile. A small slow Push In, just 2 percent. Eyes remain on the computer at screen right. At 00:00.500 the man (S1: adult 29-year-old male, warm medium-low natural Mandarin voice, relaxed conversational rhythm and dry understated humor) quietly says <d>[Chinese] 今天还挺有主见。</d> The phrase ends before 00:03.300. Start with a tiny amused exhale, lips and jaw articulate naturally while cheeks remain relaxed. A barely visible smile briefly lifts one corner of the mouth. At 00:03.800 he blinks once, lets the smile soften and lowers his gaze toward his notes. Breathing causes a very small irregular shoulder shift. No large head turn. No animals or new objects appear.\n\noverall_soundscape: Soft electric fan hum, the exact one Mandarin sentence close and intimate, a quiet breath afterward. No additional voices.\n\nnon_diegetic_music: None.",
960,
544,
158
]
},
{
"id": 8,
"type": "BasicGuider",
"pos": [
1060,
1287
],
"size": [
390,
300
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 5
},
{
"name": "conditioning",
"type": "CONDITIONING",
"link": 6
}
],
"outputs": [
{
"name": "GUIDER",
"type": "GUIDER",
"links": [
9
]
}
],
"properties": {
"Node name for S&R": "BasicGuider"
},
"widgets_values": []
},
{
"id": 9,
"type": "RandomNoise",
"pos": [
40,
410
],
"size": [
390,
300
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "NOISE",
"type": "NOISE",
"links": [
8
]
}
],
"properties": {
"Node name for S&R": "RandomNoise"
},
"widgets_values": [
86764637570136,
"fixed"
]
},
{
"id": 10,
"type": "KSamplerSelect",
"pos": [
40,
780
],
"size": [
390,
300
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "SAMPLER",
"type": "SAMPLER",
"links": [
10
]
}
],
"properties": {
"Node name for S&R": "KSamplerSelect"
},
"widgets_values": [
"res_multistep"
]
},
{
"id": 11,
"type": "BasicScheduler",
"pos": [
1060,
917
],
"size": [
390,
300
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 7
}
],
"outputs": [
{
"name": "SIGMAS",
"type": "SIGMAS",
"links": [
11
]
}
],
"properties": {
"Node name for S&R": "BasicScheduler"
},
"widgets_values": [
"simple",
8,
1.0
]
},
{
"id": 12,
"type": "SamplerCustomAdvanced",
"pos": [
1570,
1102
],
"size": [
390,
300
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "noise",
"type": "NOISE",
"link": 8
},
{
"name": "guider",
"type": "GUIDER",
"link": 9
},
{
"name": "sampler",
"type": "SAMPLER",
"link": 10
},
{
"name": "sigmas",
"type": "SIGMAS",
"link": 11
},
{
"name": "latent_image",
"type": "LATENT",
"link": 12
}
],
"outputs": [
{
"name": "output",
"type": "LATENT",
"links": [
13,
15
]
},
{
"name": "denoised_output",
"type": "LATENT",
"links": []
}
],
"properties": {
"Node name for S&R": "SamplerCustomAdvanced"
},
"widgets_values": []
},
{
"id": 13,
"type": "VAEDecode",
"pos": [
2080,
917
],
"size": [
390,
300
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 13
},
{
"name": "vae",
"type": "VAE",
"link": 14
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
17
]
}
],
"properties": {
"Node name for S&R": "VAEDecode"
},
"widgets_values": []
},
{
"id": 14,
"type": "VAEDecodeAudio",
"pos": [
2080,
1287
],
"size": [
390,
300
],
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 15
},
{
"name": "vae",
"type": "VAE",
"link": 16
}
],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
18
]
}
],
"properties": {
"Node name for S&R": "VAEDecodeAudio"
},
"widgets_values": []
},
{
"id": 15,
"type": "CreateVideo",
"pos": [
2590,
1102
],
"size": [
390,
300
],
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 17
},
{
"name": "audio",
"type": "AUDIO",
"link": 18
}
],
"outputs": [
{
"name": "VIDEO",
"type": "VIDEO",
"links": [
19
]
}
],
"properties": {
"Node name for S&R": "CreateVideo"
},
"widgets_values": [
24.0
]
},
{
"id": 16,
"type": "SaveVideo",
"pos": [
3100,
1033
],
"size": [
390,
438
],
"flags": {},
"order": 15,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": 19
}
],
"outputs": [
{
"name": "video",
"type": "VIDEO",
"links": []
}
],
"properties": {
"Node name for S&R": "SaveVideo"
},
"widgets_values": [
"hearthfire_episode/C03_V01",
"mp4",
"h264"
]
}
],
"links": [
[
1,
2,
0,
3,
0,
"MODEL"
],
[
2,
4,
0,
7,
0,
"CLIP"
],
[
3,
5,
0,
7,
1,
"VAE"
],
[
4,
1,
0,
7,
2,
"IMAGE"
],
[
5,
3,
0,
8,
0,
"MODEL"
],
[
6,
7,
0,
8,
1,
"CONDITIONING"
],
[
7,
3,
0,
11,
0,
"MODEL"
],
[
8,
9,
0,
12,
0,
"NOISE"
],
[
9,
8,
0,
12,
1,
"GUIDER"
],
[
10,
10,
0,
12,
2,
"SAMPLER"
],
[
11,
11,
0,
12,
3,
"SIGMAS"
],
[
12,
7,
1,
12,
4,
"LATENT"
],
[
13,
12,
0,
13,
0,
"LATENT"
],
[
14,
5,
0,
13,
1,
"VAE"
],
[
15,
12,
0,
14,
0,
"LATENT"
],
[
16,
6,
0,
14,
1,
"VAE"
],
[
17,
13,
0,
15,
0,
"IMAGE"
],
[
18,
14,
0,
15,
1,
"AUDIO"
],
[
19,
15,
0,
16,
0,
"VIDEO"
]
],
"groups": [
{
"title": "EP01 full episode - MiniMax H3 - native audio",
"bounding": [
-5,
-51,
3540,
2788
],
"color": "#335159",
"font_size": 24
}
],
"config": {},
"extra": {},
"version": 0.4
}
@@ -0,0 +1,57 @@
{
"file": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C03\\C03_V01_00001_.mp4",
"format": "mov,mp4,m4a,3gp,3g2,mj2",
"duration": 6.583333,
"size_bytes": 980270,
"bitrate": 1191214,
"video": {
"codec": "h264",
"profile": "High",
"width": 960,
"height": 544,
"display_aspect": "30:17",
"fps": 24.0,
"r_frame_rate": "24/1",
"avg_frame_rate": "24/1",
"variable_frame_rate_suspected": false,
"pix_fmt": "yuv420p",
"bit_depth": 8,
"hdr": false,
"hdr_signal": false,
"bt2020_or_hdr": false,
"hdr_format": null,
"dolby_vision": null,
"color_space": "bt709",
"color_primaries": "bt709",
"color_transfer": "iec61966-2-1",
"color_range": "tv",
"rotation": 0,
"nb_frames": 158,
"duration": 6.583333,
"bitrate": 1038954
},
"audio": {
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"bitrate": 129697,
"duration": 6.575
},
"subtitle_streams": 0,
"data_streams": 0,
"chapters": [],
"tags": {},
"subtitle_stream_details": [],
"audio_streams": [
{
"index": 0,
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"language": "und",
"title": null
}
]
}
@@ -0,0 +1,18 @@
{
"prompt_id": "f8aef7b3-f04a-411c-90ae-6c14583ef3fe",
"number": 97,
"node_errors": {},
"seed": 141285326704415,
"frames": 124,
"width": 960,
"height": 544,
"submitted_at": 1790658750.8858497,
"shot": {
"id": "C04",
"image": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\frames\\C04.png",
"seconds": 5,
"edit_seconds": 5,
"prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Locked close overhead shot of hands and notebook. The right hand writes two small short pencil strokes next to existing unfinished calculations, then lifts the pencil slightly. Left fingers softly adjust pressure on the notebook edge. After a thoughtful pause the left thumb raises just the corner of one page a little, the page curls naturally and settles. No full page turn, no extra fingers. Keep existing diagrams stable. No speech.\n\noverall_soundscape: Delicate pencil friction on paper, one soft paper rustle, continuous quiet fan. No voices.\n\nnon_diegetic_music: None.",
"dialogue": ""
}
}
@@ -0,0 +1,13 @@
{
"summary": "nodes=16 edges=19 overlaps=0 crossings=9 bounds=[40, 40, 3490, 2692]",
"overlaps": [],
"crossings": 9,
"bounds": [
40.0,
40.0,
3490.0,
2692.0
],
"n_nodes": 16,
"n_edges": 19
}
@@ -0,0 +1,3 @@
[
"F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C04\\C04_V01_00001_.mp4"
]
@@ -0,0 +1,7 @@
For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
integrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Locked close overhead shot of hands and notebook. The right hand writes two small short pencil strokes next to existing unfinished calculations, then lifts the pencil slightly. Left fingers softly adjust pressure on the notebook edge. After a thoughtful pause the left thumb raises just the corner of one page a little, the page curls naturally and settles. No full page turn, no extra fingers. Keep existing diagrams stable. No speech.
overall_soundscape: Delicate pencil friction on paper, one soft paper rustle, continuous quiet fan. No voices.
non_diegetic_music: None.
Binary file not shown.

After

Width:  |  Height:  |  Size: 1.1 MiB

@@ -0,0 +1,6 @@
{
"expected": "",
"recognized": "",
"segments": [],
"note": "ASR transcription, not a listening certification."
}
@@ -0,0 +1,5 @@
{
"prompt_id": "f8aef7b3-f04a-411c-90ae-6c14583ef3fe",
"number": 97,
"node_errors": {}
}
@@ -0,0 +1,181 @@
{
"1": {
"class_type": "LoadImage",
"inputs": {
"image": "hearthfire_h3/C04_C04.png"
}
},
"2": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"weight_dtype": "default"
}
},
"3": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"model": [
"2",
0
],
"lora_name": "minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
"strength_model": 1.0
}
},
"4": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"type": "minimax",
"device": "default"
}
},
"5": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "minimax_h3_video_vae_fp16.safetensors"
}
},
"6": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "minimax_h3_audio_vae_fp32.safetensors"
}
},
"7": {
"class_type": "MiniMaxH3ImageToVideo",
"inputs": {
"clip": [
"4",
0
],
"vae": [
"5",
0
],
"first_frame": [
"1",
0
],
"prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Locked close overhead shot of hands and notebook. The right hand writes two small short pencil strokes next to existing unfinished calculations, then lifts the pencil slightly. Left fingers softly adjust pressure on the notebook edge. After a thoughtful pause the left thumb raises just the corner of one page a little, the page curls naturally and settles. No full page turn, no extra fingers. Keep existing diagrams stable. No speech.\n\noverall_soundscape: Delicate pencil friction on paper, one soft paper rustle, continuous quiet fan. No voices.\n\nnon_diegetic_music: None.",
"width": 960,
"height": 544,
"length": 124
}
},
"8": {
"class_type": "BasicGuider",
"inputs": {
"model": [
"3",
0
],
"conditioning": [
"7",
0
]
}
},
"9": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 141285326704415
}
},
"10": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "res_multistep"
}
},
"11": {
"class_type": "BasicScheduler",
"inputs": {
"model": [
"3",
0
],
"scheduler": "simple",
"steps": 8,
"denoise": 1.0
}
},
"12": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"noise": [
"9",
0
],
"guider": [
"8",
0
],
"sampler": [
"10",
0
],
"sigmas": [
"11",
0
],
"latent_image": [
"7",
1
]
}
},
"13": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"12",
0
],
"vae": [
"5",
0
]
}
},
"14": {
"class_type": "VAEDecodeAudio",
"inputs": {
"samples": [
"12",
0
],
"vae": [
"6",
0
]
}
},
"15": {
"class_type": "CreateVideo",
"inputs": {
"images": [
"13",
0
],
"audio": [
"14",
0
],
"fps": 24.0
}
},
"16": {
"class_type": "SaveVideo",
"inputs": {
"video": [
"15",
0
],
"filename_prefix": "hearthfire_episode/C04_V01",
"format": "mp4",
"codec": "h264"
}
}
}
@@ -0,0 +1,804 @@
{
"last_node_id": 16,
"last_link_id": 19,
"nodes": [
{
"id": 1,
"type": "LoadImage",
"pos": [
40,
1890
],
"size": [
390,
432
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
4
]
},
{
"name": "MASK",
"type": "MASK",
"links": []
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"hearthfire_h3/C04_C04.png",
"image"
]
},
{
"id": 2,
"type": "UNETLoader",
"pos": [
40,
40
],
"size": [
390,
300
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
1
]
}
],
"properties": {
"Node name for S&R": "UNETLoader"
},
"widgets_values": [
"minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"default"
]
},
{
"id": 3,
"type": "LoraLoaderModelOnly",
"pos": [
550,
964
],
"size": [
390,
300
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 1
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
5,
7
]
}
],
"properties": {
"Node name for S&R": "LoraLoaderModelOnly"
},
"widgets_values": [
"minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
1.0
]
},
{
"id": 4,
"type": "CLIPLoader",
"pos": [
40,
2392
],
"size": [
390,
300
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
2
]
}
],
"properties": {
"Node name for S&R": "CLIPLoader"
},
"widgets_values": [
"qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"minimax",
"default"
]
},
{
"id": 5,
"type": "VAELoader",
"pos": [
40,
1150
],
"size": [
390,
300
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
3,
14
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"minimax_h3_video_vae_fp16.safetensors"
]
},
{
"id": 6,
"type": "VAELoader",
"pos": [
40,
1520
],
"size": [
390,
300
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
16
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"minimax_h3_audio_vae_fp32.safetensors"
]
},
{
"id": 7,
"type": "MiniMaxH3ImageToVideo",
"pos": [
550,
1334
],
"size": [
390,
300
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 2
},
{
"name": "vae",
"type": "VAE",
"link": 3
},
{
"name": "first_frame",
"type": "IMAGE",
"link": 4
},
{
"name": "last_frame",
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"name": "positive",
"type": "CONDITIONING",
"links": [
6
]
},
{
"name": "LATENT",
"type": "LATENT",
"links": [
12
]
}
],
"properties": {
"Node name for S&R": "MiniMaxH3ImageToVideo"
},
"widgets_values": [
"For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Locked close overhead shot of hands and notebook. The right hand writes two small short pencil strokes next to existing unfinished calculations, then lifts the pencil slightly. Left fingers softly adjust pressure on the notebook edge. After a thoughtful pause the left thumb raises just the corner of one page a little, the page curls naturally and settles. No full page turn, no extra fingers. Keep existing diagrams stable. No speech.\n\noverall_soundscape: Delicate pencil friction on paper, one soft paper rustle, continuous quiet fan. No voices.\n\nnon_diegetic_music: None.",
960,
544,
124
]
},
{
"id": 8,
"type": "BasicGuider",
"pos": [
1060,
1287
],
"size": [
390,
300
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 5
},
{
"name": "conditioning",
"type": "CONDITIONING",
"link": 6
}
],
"outputs": [
{
"name": "GUIDER",
"type": "GUIDER",
"links": [
9
]
}
],
"properties": {
"Node name for S&R": "BasicGuider"
},
"widgets_values": []
},
{
"id": 9,
"type": "RandomNoise",
"pos": [
40,
410
],
"size": [
390,
300
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "NOISE",
"type": "NOISE",
"links": [
8
]
}
],
"properties": {
"Node name for S&R": "RandomNoise"
},
"widgets_values": [
141285326704415,
"fixed"
]
},
{
"id": 10,
"type": "KSamplerSelect",
"pos": [
40,
780
],
"size": [
390,
300
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "SAMPLER",
"type": "SAMPLER",
"links": [
10
]
}
],
"properties": {
"Node name for S&R": "KSamplerSelect"
},
"widgets_values": [
"res_multistep"
]
},
{
"id": 11,
"type": "BasicScheduler",
"pos": [
1060,
917
],
"size": [
390,
300
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 7
}
],
"outputs": [
{
"name": "SIGMAS",
"type": "SIGMAS",
"links": [
11
]
}
],
"properties": {
"Node name for S&R": "BasicScheduler"
},
"widgets_values": [
"simple",
8,
1.0
]
},
{
"id": 12,
"type": "SamplerCustomAdvanced",
"pos": [
1570,
1102
],
"size": [
390,
300
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "noise",
"type": "NOISE",
"link": 8
},
{
"name": "guider",
"type": "GUIDER",
"link": 9
},
{
"name": "sampler",
"type": "SAMPLER",
"link": 10
},
{
"name": "sigmas",
"type": "SIGMAS",
"link": 11
},
{
"name": "latent_image",
"type": "LATENT",
"link": 12
}
],
"outputs": [
{
"name": "output",
"type": "LATENT",
"links": [
13,
15
]
},
{
"name": "denoised_output",
"type": "LATENT",
"links": []
}
],
"properties": {
"Node name for S&R": "SamplerCustomAdvanced"
},
"widgets_values": []
},
{
"id": 13,
"type": "VAEDecode",
"pos": [
2080,
917
],
"size": [
390,
300
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 13
},
{
"name": "vae",
"type": "VAE",
"link": 14
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
17
]
}
],
"properties": {
"Node name for S&R": "VAEDecode"
},
"widgets_values": []
},
{
"id": 14,
"type": "VAEDecodeAudio",
"pos": [
2080,
1287
],
"size": [
390,
300
],
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 15
},
{
"name": "vae",
"type": "VAE",
"link": 16
}
],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
18
]
}
],
"properties": {
"Node name for S&R": "VAEDecodeAudio"
},
"widgets_values": []
},
{
"id": 15,
"type": "CreateVideo",
"pos": [
2590,
1102
],
"size": [
390,
300
],
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 17
},
{
"name": "audio",
"type": "AUDIO",
"link": 18
}
],
"outputs": [
{
"name": "VIDEO",
"type": "VIDEO",
"links": [
19
]
}
],
"properties": {
"Node name for S&R": "CreateVideo"
},
"widgets_values": [
24.0
]
},
{
"id": 16,
"type": "SaveVideo",
"pos": [
3100,
1033
],
"size": [
390,
438
],
"flags": {},
"order": 15,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": 19
}
],
"outputs": [
{
"name": "video",
"type": "VIDEO",
"links": []
}
],
"properties": {
"Node name for S&R": "SaveVideo"
},
"widgets_values": [
"hearthfire_episode/C04_V01",
"mp4",
"h264"
]
}
],
"links": [
[
1,
2,
0,
3,
0,
"MODEL"
],
[
2,
4,
0,
7,
0,
"CLIP"
],
[
3,
5,
0,
7,
1,
"VAE"
],
[
4,
1,
0,
7,
2,
"IMAGE"
],
[
5,
3,
0,
8,
0,
"MODEL"
],
[
6,
7,
0,
8,
1,
"CONDITIONING"
],
[
7,
3,
0,
11,
0,
"MODEL"
],
[
8,
9,
0,
12,
0,
"NOISE"
],
[
9,
8,
0,
12,
1,
"GUIDER"
],
[
10,
10,
0,
12,
2,
"SAMPLER"
],
[
11,
11,
0,
12,
3,
"SIGMAS"
],
[
12,
7,
1,
12,
4,
"LATENT"
],
[
13,
12,
0,
13,
0,
"LATENT"
],
[
14,
5,
0,
13,
1,
"VAE"
],
[
15,
12,
0,
14,
0,
"LATENT"
],
[
16,
6,
0,
14,
1,
"VAE"
],
[
17,
13,
0,
15,
0,
"IMAGE"
],
[
18,
14,
0,
15,
1,
"AUDIO"
],
[
19,
15,
0,
16,
0,
"VIDEO"
]
],
"groups": [
{
"title": "EP01 full episode - MiniMax H3 - native audio",
"bounding": [
-5,
-51,
3540,
2788
],
"color": "#335159",
"font_size": 24
}
],
"config": {},
"extra": {},
"version": 0.4
}
@@ -0,0 +1,57 @@
{
"file": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C04\\C04_V01_00001_.mp4",
"format": "mov,mp4,m4a,3gp,3g2,mj2",
"duration": 5.167,
"size_bytes": 910442,
"bitrate": 1409625,
"video": {
"codec": "h264",
"profile": "High",
"width": 960,
"height": 544,
"display_aspect": "30:17",
"fps": 24.0,
"r_frame_rate": "24/1",
"avg_frame_rate": "24/1",
"variable_frame_rate_suspected": false,
"pix_fmt": "yuv420p",
"bit_depth": 8,
"hdr": false,
"hdr_signal": false,
"bt2020_or_hdr": false,
"hdr_format": null,
"dolby_vision": null,
"color_space": "bt709",
"color_primaries": "bt709",
"color_transfer": "iec61966-2-1",
"color_range": "tv",
"rotation": 0,
"nb_frames": 124,
"duration": 5.166667,
"bitrate": 1253758
},
"audio": {
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"bitrate": 129703,
"duration": 5.167
},
"subtitle_streams": 0,
"data_streams": 0,
"chapters": [],
"tags": {},
"subtitle_stream_details": [],
"audio_streams": [
{
"index": 0,
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"language": "und",
"title": null
}
]
}
@@ -0,0 +1,18 @@
{
"prompt_id": "7e79b980-e120-4be4-98cf-cde2362b2641",
"number": 98,
"node_errors": {},
"seed": 120467321486742,
"frames": 158,
"width": 960,
"height": 544,
"submitted_at": 1790658913.8003876,
"shot": {
"id": "C05",
"image": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\frames\\C05.png",
"seconds": 6,
"edit_seconds": 6,
"prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Fixed medium side shot. At 00:00.300 the small alarm sounds. His eyes shift toward it BEFORE his head turns slightly. His right mouse hand hesitates, fingers relaxed, then one quiet inhale. At 00:02.600 he makes two small deliberate mouse clicks, saves and shuts down. The screen is out of view. His shoulders release on an exhale, his right hand slips away from the mouse to his lap at 00:04.500. One natural blink. He remains seated throughout, mouth closed, expression gently tired, not sad. No speech.\n\noverall_soundscape: A brief gentle alarm beep, two crisp mouse clicks, a soft relaxed breath and steady fan bearing ambience. No voices.\n\nnon_diegetic_music: None.",
"dialogue": ""
}
}
@@ -0,0 +1,13 @@
{
"summary": "nodes=16 edges=19 overlaps=0 crossings=9 bounds=[40, 40, 3490, 2692]",
"overlaps": [],
"crossings": 9,
"bounds": [
40.0,
40.0,
3490.0,
2692.0
],
"n_nodes": 16,
"n_edges": 19
}
@@ -0,0 +1,3 @@
[
"F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C05\\C05_V01_00001_.mp4"
]
@@ -0,0 +1,7 @@
For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
integrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Fixed medium side shot. At 00:00.300 the small alarm sounds. His eyes shift toward it BEFORE his head turns slightly. His right mouse hand hesitates, fingers relaxed, then one quiet inhale. At 00:02.600 he makes two small deliberate mouse clicks, saves and shuts down. The screen is out of view. His shoulders release on an exhale, his right hand slips away from the mouse to his lap at 00:04.500. One natural blink. He remains seated throughout, mouth closed, expression gently tired, not sad. No speech.
overall_soundscape: A brief gentle alarm beep, two crisp mouse clicks, a soft relaxed breath and steady fan bearing ambience. No voices.
non_diegetic_music: None.
Binary file not shown.

After

Width:  |  Height:  |  Size: 1.2 MiB

@@ -0,0 +1,6 @@
{
"expected": "",
"recognized": "",
"segments": [],
"note": "ASR transcription, not a listening certification."
}
@@ -0,0 +1,5 @@
{
"prompt_id": "7e79b980-e120-4be4-98cf-cde2362b2641",
"number": 98,
"node_errors": {}
}
@@ -0,0 +1,181 @@
{
"1": {
"class_type": "LoadImage",
"inputs": {
"image": "hearthfire_h3/C05_C05.png"
}
},
"2": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"weight_dtype": "default"
}
},
"3": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"model": [
"2",
0
],
"lora_name": "minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
"strength_model": 1.0
}
},
"4": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"type": "minimax",
"device": "default"
}
},
"5": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "minimax_h3_video_vae_fp16.safetensors"
}
},
"6": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "minimax_h3_audio_vae_fp32.safetensors"
}
},
"7": {
"class_type": "MiniMaxH3ImageToVideo",
"inputs": {
"clip": [
"4",
0
],
"vae": [
"5",
0
],
"first_frame": [
"1",
0
],
"prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Fixed medium side shot. At 00:00.300 the small alarm sounds. His eyes shift toward it BEFORE his head turns slightly. His right mouse hand hesitates, fingers relaxed, then one quiet inhale. At 00:02.600 he makes two small deliberate mouse clicks, saves and shuts down. The screen is out of view. His shoulders release on an exhale, his right hand slips away from the mouse to his lap at 00:04.500. One natural blink. He remains seated throughout, mouth closed, expression gently tired, not sad. No speech.\n\noverall_soundscape: A brief gentle alarm beep, two crisp mouse clicks, a soft relaxed breath and steady fan bearing ambience. No voices.\n\nnon_diegetic_music: None.",
"width": 960,
"height": 544,
"length": 158
}
},
"8": {
"class_type": "BasicGuider",
"inputs": {
"model": [
"3",
0
],
"conditioning": [
"7",
0
]
}
},
"9": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 120467321486742
}
},
"10": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "res_multistep"
}
},
"11": {
"class_type": "BasicScheduler",
"inputs": {
"model": [
"3",
0
],
"scheduler": "simple",
"steps": 8,
"denoise": 1.0
}
},
"12": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"noise": [
"9",
0
],
"guider": [
"8",
0
],
"sampler": [
"10",
0
],
"sigmas": [
"11",
0
],
"latent_image": [
"7",
1
]
}
},
"13": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"12",
0
],
"vae": [
"5",
0
]
}
},
"14": {
"class_type": "VAEDecodeAudio",
"inputs": {
"samples": [
"12",
0
],
"vae": [
"6",
0
]
}
},
"15": {
"class_type": "CreateVideo",
"inputs": {
"images": [
"13",
0
],
"audio": [
"14",
0
],
"fps": 24.0
}
},
"16": {
"class_type": "SaveVideo",
"inputs": {
"video": [
"15",
0
],
"filename_prefix": "hearthfire_episode/C05_V01",
"format": "mp4",
"codec": "h264"
}
}
}
@@ -0,0 +1,804 @@
{
"last_node_id": 16,
"last_link_id": 19,
"nodes": [
{
"id": 1,
"type": "LoadImage",
"pos": [
40,
1890
],
"size": [
390,
432
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
4
]
},
{
"name": "MASK",
"type": "MASK",
"links": []
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"hearthfire_h3/C05_C05.png",
"image"
]
},
{
"id": 2,
"type": "UNETLoader",
"pos": [
40,
40
],
"size": [
390,
300
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
1
]
}
],
"properties": {
"Node name for S&R": "UNETLoader"
},
"widgets_values": [
"minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"default"
]
},
{
"id": 3,
"type": "LoraLoaderModelOnly",
"pos": [
550,
964
],
"size": [
390,
300
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 1
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
5,
7
]
}
],
"properties": {
"Node name for S&R": "LoraLoaderModelOnly"
},
"widgets_values": [
"minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
1.0
]
},
{
"id": 4,
"type": "CLIPLoader",
"pos": [
40,
2392
],
"size": [
390,
300
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
2
]
}
],
"properties": {
"Node name for S&R": "CLIPLoader"
},
"widgets_values": [
"qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"minimax",
"default"
]
},
{
"id": 5,
"type": "VAELoader",
"pos": [
40,
1150
],
"size": [
390,
300
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
3,
14
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"minimax_h3_video_vae_fp16.safetensors"
]
},
{
"id": 6,
"type": "VAELoader",
"pos": [
40,
1520
],
"size": [
390,
300
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
16
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"minimax_h3_audio_vae_fp32.safetensors"
]
},
{
"id": 7,
"type": "MiniMaxH3ImageToVideo",
"pos": [
550,
1334
],
"size": [
390,
300
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 2
},
{
"name": "vae",
"type": "VAE",
"link": 3
},
{
"name": "first_frame",
"type": "IMAGE",
"link": 4
},
{
"name": "last_frame",
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"name": "positive",
"type": "CONDITIONING",
"links": [
6
]
},
{
"name": "LATENT",
"type": "LATENT",
"links": [
12
]
}
],
"properties": {
"Node name for S&R": "MiniMaxH3ImageToVideo"
},
"widgets_values": [
"For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Fixed medium side shot. At 00:00.300 the small alarm sounds. His eyes shift toward it BEFORE his head turns slightly. His right mouse hand hesitates, fingers relaxed, then one quiet inhale. At 00:02.600 he makes two small deliberate mouse clicks, saves and shuts down. The screen is out of view. His shoulders release on an exhale, his right hand slips away from the mouse to his lap at 00:04.500. One natural blink. He remains seated throughout, mouth closed, expression gently tired, not sad. No speech.\n\noverall_soundscape: A brief gentle alarm beep, two crisp mouse clicks, a soft relaxed breath and steady fan bearing ambience. No voices.\n\nnon_diegetic_music: None.",
960,
544,
158
]
},
{
"id": 8,
"type": "BasicGuider",
"pos": [
1060,
1287
],
"size": [
390,
300
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 5
},
{
"name": "conditioning",
"type": "CONDITIONING",
"link": 6
}
],
"outputs": [
{
"name": "GUIDER",
"type": "GUIDER",
"links": [
9
]
}
],
"properties": {
"Node name for S&R": "BasicGuider"
},
"widgets_values": []
},
{
"id": 9,
"type": "RandomNoise",
"pos": [
40,
410
],
"size": [
390,
300
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "NOISE",
"type": "NOISE",
"links": [
8
]
}
],
"properties": {
"Node name for S&R": "RandomNoise"
},
"widgets_values": [
120467321486742,
"fixed"
]
},
{
"id": 10,
"type": "KSamplerSelect",
"pos": [
40,
780
],
"size": [
390,
300
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "SAMPLER",
"type": "SAMPLER",
"links": [
10
]
}
],
"properties": {
"Node name for S&R": "KSamplerSelect"
},
"widgets_values": [
"res_multistep"
]
},
{
"id": 11,
"type": "BasicScheduler",
"pos": [
1060,
917
],
"size": [
390,
300
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 7
}
],
"outputs": [
{
"name": "SIGMAS",
"type": "SIGMAS",
"links": [
11
]
}
],
"properties": {
"Node name for S&R": "BasicScheduler"
},
"widgets_values": [
"simple",
8,
1.0
]
},
{
"id": 12,
"type": "SamplerCustomAdvanced",
"pos": [
1570,
1102
],
"size": [
390,
300
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "noise",
"type": "NOISE",
"link": 8
},
{
"name": "guider",
"type": "GUIDER",
"link": 9
},
{
"name": "sampler",
"type": "SAMPLER",
"link": 10
},
{
"name": "sigmas",
"type": "SIGMAS",
"link": 11
},
{
"name": "latent_image",
"type": "LATENT",
"link": 12
}
],
"outputs": [
{
"name": "output",
"type": "LATENT",
"links": [
13,
15
]
},
{
"name": "denoised_output",
"type": "LATENT",
"links": []
}
],
"properties": {
"Node name for S&R": "SamplerCustomAdvanced"
},
"widgets_values": []
},
{
"id": 13,
"type": "VAEDecode",
"pos": [
2080,
917
],
"size": [
390,
300
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 13
},
{
"name": "vae",
"type": "VAE",
"link": 14
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
17
]
}
],
"properties": {
"Node name for S&R": "VAEDecode"
},
"widgets_values": []
},
{
"id": 14,
"type": "VAEDecodeAudio",
"pos": [
2080,
1287
],
"size": [
390,
300
],
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 15
},
{
"name": "vae",
"type": "VAE",
"link": 16
}
],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
18
]
}
],
"properties": {
"Node name for S&R": "VAEDecodeAudio"
},
"widgets_values": []
},
{
"id": 15,
"type": "CreateVideo",
"pos": [
2590,
1102
],
"size": [
390,
300
],
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 17
},
{
"name": "audio",
"type": "AUDIO",
"link": 18
}
],
"outputs": [
{
"name": "VIDEO",
"type": "VIDEO",
"links": [
19
]
}
],
"properties": {
"Node name for S&R": "CreateVideo"
},
"widgets_values": [
24.0
]
},
{
"id": 16,
"type": "SaveVideo",
"pos": [
3100,
1033
],
"size": [
390,
438
],
"flags": {},
"order": 15,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": 19
}
],
"outputs": [
{
"name": "video",
"type": "VIDEO",
"links": []
}
],
"properties": {
"Node name for S&R": "SaveVideo"
},
"widgets_values": [
"hearthfire_episode/C05_V01",
"mp4",
"h264"
]
}
],
"links": [
[
1,
2,
0,
3,
0,
"MODEL"
],
[
2,
4,
0,
7,
0,
"CLIP"
],
[
3,
5,
0,
7,
1,
"VAE"
],
[
4,
1,
0,
7,
2,
"IMAGE"
],
[
5,
3,
0,
8,
0,
"MODEL"
],
[
6,
7,
0,
8,
1,
"CONDITIONING"
],
[
7,
3,
0,
11,
0,
"MODEL"
],
[
8,
9,
0,
12,
0,
"NOISE"
],
[
9,
8,
0,
12,
1,
"GUIDER"
],
[
10,
10,
0,
12,
2,
"SAMPLER"
],
[
11,
11,
0,
12,
3,
"SIGMAS"
],
[
12,
7,
1,
12,
4,
"LATENT"
],
[
13,
12,
0,
13,
0,
"LATENT"
],
[
14,
5,
0,
13,
1,
"VAE"
],
[
15,
12,
0,
14,
0,
"LATENT"
],
[
16,
6,
0,
14,
1,
"VAE"
],
[
17,
13,
0,
15,
0,
"IMAGE"
],
[
18,
14,
0,
15,
1,
"AUDIO"
],
[
19,
15,
0,
16,
0,
"VIDEO"
]
],
"groups": [
{
"title": "EP01 full episode - MiniMax H3 - native audio",
"bounding": [
-5,
-51,
3540,
2788
],
"color": "#335159",
"font_size": 24
}
],
"config": {},
"extra": {},
"version": 0.4
}
@@ -0,0 +1,57 @@
{
"file": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C05\\C05_V01_00001_.mp4",
"format": "mov,mp4,m4a,3gp,3g2,mj2",
"duration": 6.583333,
"size_bytes": 949237,
"bitrate": 1153503,
"video": {
"codec": "h264",
"profile": "High",
"width": 960,
"height": 544,
"display_aspect": "30:17",
"fps": 24.0,
"r_frame_rate": "24/1",
"avg_frame_rate": "24/1",
"variable_frame_rate_suspected": false,
"pix_fmt": "yuv420p",
"bit_depth": 8,
"hdr": false,
"hdr_signal": false,
"bt2020_or_hdr": false,
"hdr_format": null,
"dolby_vision": null,
"color_space": "bt709",
"color_primaries": "bt709",
"color_transfer": "iec61966-2-1",
"color_range": "tv",
"rotation": 0,
"nb_frames": 158,
"duration": 6.583333,
"bitrate": 1003955
},
"audio": {
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"bitrate": 127581,
"duration": 6.575
},
"subtitle_streams": 0,
"data_streams": 0,
"chapters": [],
"tags": {},
"subtitle_stream_details": [],
"audio_streams": [
{
"index": 0,
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"language": "und",
"title": null
}
]
}
@@ -0,0 +1,18 @@
{
"prompt_id": "db53ddab-6570-4b48-9769-d43e9d1ea69c",
"number": 99,
"node_errors": {},
"seed": 122942981334053,
"frames": 158,
"width": 960,
"height": 544,
"submitted_at": 1790659136.7839823,
"shot": {
"id": "C06",
"image": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\frames\\C06.png",
"seconds": 6,
"edit_seconds": 6,
"prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Close waist-up three-quarter view at the window, right hand holding a small cream cup just above the almost-bare third mint pot. His eyes inspect the surviving leaves. At 00:01.000 his wrist tilts slowly, pours a small thin stream onto the SOIL for one second. He tilts the cup back upright to stop water, waits for one final drop, then carefully lowers the cup onto the sill to the right of the third pot by 00:04.500. Fingers release naturally only after the cup contacts the sill. Sparse leaves move slightly from the air, never grow. Torso subtly balances with the arm. Lips closed, no speech. Camera fixed.\n\noverall_soundscape: Quiet short trickle of water, single small ceramic-on-wood tap, soft fabric movement and continuous fan. No voices.\n\nnon_diegetic_music: None.",
"dialogue": ""
}
}
@@ -0,0 +1,13 @@
{
"summary": "nodes=16 edges=19 overlaps=0 crossings=9 bounds=[40, 40, 3490, 2692]",
"overlaps": [],
"crossings": 9,
"bounds": [
40.0,
40.0,
3490.0,
2692.0
],
"n_nodes": 16,
"n_edges": 19
}
@@ -0,0 +1,3 @@
[
"F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C06\\C06_V01_00001_.mp4"
]
@@ -0,0 +1,7 @@
For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
integrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Close waist-up three-quarter view at the window, right hand holding a small cream cup just above the almost-bare third mint pot. His eyes inspect the surviving leaves. At 00:01.000 his wrist tilts slowly, pours a small thin stream onto the SOIL for one second. He tilts the cup back upright to stop water, waits for one final drop, then carefully lowers the cup onto the sill to the right of the third pot by 00:04.500. Fingers release naturally only after the cup contacts the sill. Sparse leaves move slightly from the air, never grow. Torso subtly balances with the arm. Lips closed, no speech. Camera fixed.
overall_soundscape: Quiet short trickle of water, single small ceramic-on-wood tap, soft fabric movement and continuous fan. No voices.
non_diegetic_music: None.
Binary file not shown.

After

Width:  |  Height:  |  Size: 1.2 MiB

@@ -0,0 +1,6 @@
{
"expected": "",
"recognized": "",
"segments": [],
"note": "ASR transcription, not a listening certification."
}
@@ -0,0 +1,5 @@
{
"prompt_id": "db53ddab-6570-4b48-9769-d43e9d1ea69c",
"number": 99,
"node_errors": {}
}
@@ -0,0 +1,181 @@
{
"1": {
"class_type": "LoadImage",
"inputs": {
"image": "hearthfire_h3/C06_C06.png"
}
},
"2": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"weight_dtype": "default"
}
},
"3": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"model": [
"2",
0
],
"lora_name": "minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
"strength_model": 1.0
}
},
"4": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"type": "minimax",
"device": "default"
}
},
"5": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "minimax_h3_video_vae_fp16.safetensors"
}
},
"6": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "minimax_h3_audio_vae_fp32.safetensors"
}
},
"7": {
"class_type": "MiniMaxH3ImageToVideo",
"inputs": {
"clip": [
"4",
0
],
"vae": [
"5",
0
],
"first_frame": [
"1",
0
],
"prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Close waist-up three-quarter view at the window, right hand holding a small cream cup just above the almost-bare third mint pot. His eyes inspect the surviving leaves. At 00:01.000 his wrist tilts slowly, pours a small thin stream onto the SOIL for one second. He tilts the cup back upright to stop water, waits for one final drop, then carefully lowers the cup onto the sill to the right of the third pot by 00:04.500. Fingers release naturally only after the cup contacts the sill. Sparse leaves move slightly from the air, never grow. Torso subtly balances with the arm. Lips closed, no speech. Camera fixed.\n\noverall_soundscape: Quiet short trickle of water, single small ceramic-on-wood tap, soft fabric movement and continuous fan. No voices.\n\nnon_diegetic_music: None.",
"width": 960,
"height": 544,
"length": 158
}
},
"8": {
"class_type": "BasicGuider",
"inputs": {
"model": [
"3",
0
],
"conditioning": [
"7",
0
]
}
},
"9": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 122942981334053
}
},
"10": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "res_multistep"
}
},
"11": {
"class_type": "BasicScheduler",
"inputs": {
"model": [
"3",
0
],
"scheduler": "simple",
"steps": 8,
"denoise": 1.0
}
},
"12": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"noise": [
"9",
0
],
"guider": [
"8",
0
],
"sampler": [
"10",
0
],
"sigmas": [
"11",
0
],
"latent_image": [
"7",
1
]
}
},
"13": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"12",
0
],
"vae": [
"5",
0
]
}
},
"14": {
"class_type": "VAEDecodeAudio",
"inputs": {
"samples": [
"12",
0
],
"vae": [
"6",
0
]
}
},
"15": {
"class_type": "CreateVideo",
"inputs": {
"images": [
"13",
0
],
"audio": [
"14",
0
],
"fps": 24.0
}
},
"16": {
"class_type": "SaveVideo",
"inputs": {
"video": [
"15",
0
],
"filename_prefix": "hearthfire_episode/C06_V01",
"format": "mp4",
"codec": "h264"
}
}
}
@@ -0,0 +1,804 @@
{
"last_node_id": 16,
"last_link_id": 19,
"nodes": [
{
"id": 1,
"type": "LoadImage",
"pos": [
40,
1890
],
"size": [
390,
432
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
4
]
},
{
"name": "MASK",
"type": "MASK",
"links": []
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"hearthfire_h3/C06_C06.png",
"image"
]
},
{
"id": 2,
"type": "UNETLoader",
"pos": [
40,
40
],
"size": [
390,
300
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
1
]
}
],
"properties": {
"Node name for S&R": "UNETLoader"
},
"widgets_values": [
"minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"default"
]
},
{
"id": 3,
"type": "LoraLoaderModelOnly",
"pos": [
550,
964
],
"size": [
390,
300
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 1
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
5,
7
]
}
],
"properties": {
"Node name for S&R": "LoraLoaderModelOnly"
},
"widgets_values": [
"minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
1.0
]
},
{
"id": 4,
"type": "CLIPLoader",
"pos": [
40,
2392
],
"size": [
390,
300
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
2
]
}
],
"properties": {
"Node name for S&R": "CLIPLoader"
},
"widgets_values": [
"qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"minimax",
"default"
]
},
{
"id": 5,
"type": "VAELoader",
"pos": [
40,
1150
],
"size": [
390,
300
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
3,
14
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"minimax_h3_video_vae_fp16.safetensors"
]
},
{
"id": 6,
"type": "VAELoader",
"pos": [
40,
1520
],
"size": [
390,
300
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
16
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"minimax_h3_audio_vae_fp32.safetensors"
]
},
{
"id": 7,
"type": "MiniMaxH3ImageToVideo",
"pos": [
550,
1334
],
"size": [
390,
300
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 2
},
{
"name": "vae",
"type": "VAE",
"link": 3
},
{
"name": "first_frame",
"type": "IMAGE",
"link": 4
},
{
"name": "last_frame",
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"name": "positive",
"type": "CONDITIONING",
"links": [
6
]
},
{
"name": "LATENT",
"type": "LATENT",
"links": [
12
]
}
],
"properties": {
"Node name for S&R": "MiniMaxH3ImageToVideo"
},
"widgets_values": [
"For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Close waist-up three-quarter view at the window, right hand holding a small cream cup just above the almost-bare third mint pot. His eyes inspect the surviving leaves. At 00:01.000 his wrist tilts slowly, pours a small thin stream onto the SOIL for one second. He tilts the cup back upright to stop water, waits for one final drop, then carefully lowers the cup onto the sill to the right of the third pot by 00:04.500. Fingers release naturally only after the cup contacts the sill. Sparse leaves move slightly from the air, never grow. Torso subtly balances with the arm. Lips closed, no speech. Camera fixed.\n\noverall_soundscape: Quiet short trickle of water, single small ceramic-on-wood tap, soft fabric movement and continuous fan. No voices.\n\nnon_diegetic_music: None.",
960,
544,
158
]
},
{
"id": 8,
"type": "BasicGuider",
"pos": [
1060,
1287
],
"size": [
390,
300
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 5
},
{
"name": "conditioning",
"type": "CONDITIONING",
"link": 6
}
],
"outputs": [
{
"name": "GUIDER",
"type": "GUIDER",
"links": [
9
]
}
],
"properties": {
"Node name for S&R": "BasicGuider"
},
"widgets_values": []
},
{
"id": 9,
"type": "RandomNoise",
"pos": [
40,
410
],
"size": [
390,
300
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "NOISE",
"type": "NOISE",
"links": [
8
]
}
],
"properties": {
"Node name for S&R": "RandomNoise"
},
"widgets_values": [
122942981334053,
"fixed"
]
},
{
"id": 10,
"type": "KSamplerSelect",
"pos": [
40,
780
],
"size": [
390,
300
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "SAMPLER",
"type": "SAMPLER",
"links": [
10
]
}
],
"properties": {
"Node name for S&R": "KSamplerSelect"
},
"widgets_values": [
"res_multistep"
]
},
{
"id": 11,
"type": "BasicScheduler",
"pos": [
1060,
917
],
"size": [
390,
300
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 7
}
],
"outputs": [
{
"name": "SIGMAS",
"type": "SIGMAS",
"links": [
11
]
}
],
"properties": {
"Node name for S&R": "BasicScheduler"
},
"widgets_values": [
"simple",
8,
1.0
]
},
{
"id": 12,
"type": "SamplerCustomAdvanced",
"pos": [
1570,
1102
],
"size": [
390,
300
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "noise",
"type": "NOISE",
"link": 8
},
{
"name": "guider",
"type": "GUIDER",
"link": 9
},
{
"name": "sampler",
"type": "SAMPLER",
"link": 10
},
{
"name": "sigmas",
"type": "SIGMAS",
"link": 11
},
{
"name": "latent_image",
"type": "LATENT",
"link": 12
}
],
"outputs": [
{
"name": "output",
"type": "LATENT",
"links": [
13,
15
]
},
{
"name": "denoised_output",
"type": "LATENT",
"links": []
}
],
"properties": {
"Node name for S&R": "SamplerCustomAdvanced"
},
"widgets_values": []
},
{
"id": 13,
"type": "VAEDecode",
"pos": [
2080,
917
],
"size": [
390,
300
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 13
},
{
"name": "vae",
"type": "VAE",
"link": 14
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
17
]
}
],
"properties": {
"Node name for S&R": "VAEDecode"
},
"widgets_values": []
},
{
"id": 14,
"type": "VAEDecodeAudio",
"pos": [
2080,
1287
],
"size": [
390,
300
],
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 15
},
{
"name": "vae",
"type": "VAE",
"link": 16
}
],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
18
]
}
],
"properties": {
"Node name for S&R": "VAEDecodeAudio"
},
"widgets_values": []
},
{
"id": 15,
"type": "CreateVideo",
"pos": [
2590,
1102
],
"size": [
390,
300
],
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 17
},
{
"name": "audio",
"type": "AUDIO",
"link": 18
}
],
"outputs": [
{
"name": "VIDEO",
"type": "VIDEO",
"links": [
19
]
}
],
"properties": {
"Node name for S&R": "CreateVideo"
},
"widgets_values": [
24.0
]
},
{
"id": 16,
"type": "SaveVideo",
"pos": [
3100,
1033
],
"size": [
390,
438
],
"flags": {},
"order": 15,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": 19
}
],
"outputs": [
{
"name": "video",
"type": "VIDEO",
"links": []
}
],
"properties": {
"Node name for S&R": "SaveVideo"
},
"widgets_values": [
"hearthfire_episode/C06_V01",
"mp4",
"h264"
]
}
],
"links": [
[
1,
2,
0,
3,
0,
"MODEL"
],
[
2,
4,
0,
7,
0,
"CLIP"
],
[
3,
5,
0,
7,
1,
"VAE"
],
[
4,
1,
0,
7,
2,
"IMAGE"
],
[
5,
3,
0,
8,
0,
"MODEL"
],
[
6,
7,
0,
8,
1,
"CONDITIONING"
],
[
7,
3,
0,
11,
0,
"MODEL"
],
[
8,
9,
0,
12,
0,
"NOISE"
],
[
9,
8,
0,
12,
1,
"GUIDER"
],
[
10,
10,
0,
12,
2,
"SAMPLER"
],
[
11,
11,
0,
12,
3,
"SIGMAS"
],
[
12,
7,
1,
12,
4,
"LATENT"
],
[
13,
12,
0,
13,
0,
"LATENT"
],
[
14,
5,
0,
13,
1,
"VAE"
],
[
15,
12,
0,
14,
0,
"LATENT"
],
[
16,
6,
0,
14,
1,
"VAE"
],
[
17,
13,
0,
15,
0,
"IMAGE"
],
[
18,
14,
0,
15,
1,
"AUDIO"
],
[
19,
15,
0,
16,
0,
"VIDEO"
]
],
"groups": [
{
"title": "EP01 full episode - MiniMax H3 - native audio",
"bounding": [
-5,
-51,
3540,
2788
],
"color": "#335159",
"font_size": 24
}
],
"config": {},
"extra": {},
"version": 0.4
}
@@ -0,0 +1,57 @@
{
"file": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C06\\C06_V01_00001_.mp4",
"format": "mov,mp4,m4a,3gp,3g2,mj2",
"duration": 6.583333,
"size_bytes": 782204,
"bitrate": 950526,
"video": {
"codec": "h264",
"profile": "High",
"width": 960,
"height": 544,
"display_aspect": "30:17",
"fps": 24.0,
"r_frame_rate": "24/1",
"avg_frame_rate": "24/1",
"variable_frame_rate_suspected": false,
"pix_fmt": "yuv420p",
"bit_depth": 8,
"hdr": false,
"hdr_signal": false,
"bt2020_or_hdr": false,
"hdr_format": null,
"dolby_vision": null,
"color_space": "bt709",
"color_primaries": "bt709",
"color_transfer": "iec61966-2-1",
"color_range": "tv",
"rotation": 0,
"nb_frames": 158,
"duration": 6.583333,
"bitrate": 792823
},
"audio": {
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"bitrate": 135423,
"duration": 6.575
},
"subtitle_streams": 0,
"data_streams": 0,
"chapters": [],
"tags": {},
"subtitle_stream_details": [],
"audio_streams": [
{
"index": 0,
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"language": "und",
"title": null
}
]
}
@@ -0,0 +1,18 @@
{
"prompt_id": "aef0e157-7c64-4f67-937f-a55ac8df7d18",
"number": 100,
"node_errors": {},
"seed": 147096411546182,
"frames": 158,
"width": 960,
"height": 544,
"submitted_at": 1790659359.740271,
"shot": {
"id": "C07",
"image": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\frames\\C07.png",
"seconds": 6,
"edit_seconds": 6,
"prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Wide shot. The same man is standing by the window after watering, cream cup already rests on the sill. His eyes follow the curtain edge, then his LEFT hand reaches and grasps it. He draws the curtain gently across the window during 00:01.000 to 00:03.000. Fabric follows his hand with soft delayed folds, daylight slowly dims to a muted lavender interior; it does not go black. He releases the curtain, pauses, shifts his weight onto his right foot, turns toward the bed at back right and takes two relaxed short steps. Arms swing a little out of phase with the legs, shoulders and hips turn naturally. No sliding feet. Bed, chair and furniture stay fixed. Camera stationary, no speech.\n\noverall_soundscape: Soft curtain rings and cloth, two quiet slipper footsteps, unchanged fan hum. No voices.\n\nnon_diegetic_music: None.",
"dialogue": ""
}
}
@@ -0,0 +1,13 @@
{
"summary": "nodes=16 edges=19 overlaps=0 crossings=9 bounds=[40, 40, 3490, 2692]",
"overlaps": [],
"crossings": 9,
"bounds": [
40.0,
40.0,
3490.0,
2692.0
],
"n_nodes": 16,
"n_edges": 19
}
@@ -0,0 +1,3 @@
[
"F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C07\\C07_V01_00001_.mp4"
]
@@ -0,0 +1,7 @@
For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
integrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Wide shot. The same man is standing by the window after watering, cream cup already rests on the sill. His eyes follow the curtain edge, then his LEFT hand reaches and grasps it. He draws the curtain gently across the window during 00:01.000 to 00:03.000. Fabric follows his hand with soft delayed folds, daylight slowly dims to a muted lavender interior; it does not go black. He releases the curtain, pauses, shifts his weight onto his right foot, turns toward the bed at back right and takes two relaxed short steps. Arms swing a little out of phase with the legs, shoulders and hips turn naturally. No sliding feet. Bed, chair and furniture stay fixed. Camera stationary, no speech.
overall_soundscape: Soft curtain rings and cloth, two quiet slipper footsteps, unchanged fan hum. No voices.
non_diegetic_music: None.
Binary file not shown.

After

Width:  |  Height:  |  Size: 1.1 MiB

@@ -0,0 +1,6 @@
{
"expected": "",
"recognized": "",
"segments": [],
"note": "ASR transcription, not a listening certification."
}
@@ -0,0 +1,5 @@
{
"prompt_id": "aef0e157-7c64-4f67-937f-a55ac8df7d18",
"number": 100,
"node_errors": {}
}
@@ -0,0 +1,181 @@
{
"1": {
"class_type": "LoadImage",
"inputs": {
"image": "hearthfire_h3/C07_C07.png"
}
},
"2": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"weight_dtype": "default"
}
},
"3": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"model": [
"2",
0
],
"lora_name": "minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
"strength_model": 1.0
}
},
"4": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"type": "minimax",
"device": "default"
}
},
"5": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "minimax_h3_video_vae_fp16.safetensors"
}
},
"6": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "minimax_h3_audio_vae_fp32.safetensors"
}
},
"7": {
"class_type": "MiniMaxH3ImageToVideo",
"inputs": {
"clip": [
"4",
0
],
"vae": [
"5",
0
],
"first_frame": [
"1",
0
],
"prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Wide shot. The same man is standing by the window after watering, cream cup already rests on the sill. His eyes follow the curtain edge, then his LEFT hand reaches and grasps it. He draws the curtain gently across the window during 00:01.000 to 00:03.000. Fabric follows his hand with soft delayed folds, daylight slowly dims to a muted lavender interior; it does not go black. He releases the curtain, pauses, shifts his weight onto his right foot, turns toward the bed at back right and takes two relaxed short steps. Arms swing a little out of phase with the legs, shoulders and hips turn naturally. No sliding feet. Bed, chair and furniture stay fixed. Camera stationary, no speech.\n\noverall_soundscape: Soft curtain rings and cloth, two quiet slipper footsteps, unchanged fan hum. No voices.\n\nnon_diegetic_music: None.",
"width": 960,
"height": 544,
"length": 158
}
},
"8": {
"class_type": "BasicGuider",
"inputs": {
"model": [
"3",
0
],
"conditioning": [
"7",
0
]
}
},
"9": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 147096411546182
}
},
"10": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "res_multistep"
}
},
"11": {
"class_type": "BasicScheduler",
"inputs": {
"model": [
"3",
0
],
"scheduler": "simple",
"steps": 8,
"denoise": 1.0
}
},
"12": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"noise": [
"9",
0
],
"guider": [
"8",
0
],
"sampler": [
"10",
0
],
"sigmas": [
"11",
0
],
"latent_image": [
"7",
1
]
}
},
"13": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"12",
0
],
"vae": [
"5",
0
]
}
},
"14": {
"class_type": "VAEDecodeAudio",
"inputs": {
"samples": [
"12",
0
],
"vae": [
"6",
0
]
}
},
"15": {
"class_type": "CreateVideo",
"inputs": {
"images": [
"13",
0
],
"audio": [
"14",
0
],
"fps": 24.0
}
},
"16": {
"class_type": "SaveVideo",
"inputs": {
"video": [
"15",
0
],
"filename_prefix": "hearthfire_episode/C07_V01",
"format": "mp4",
"codec": "h264"
}
}
}
@@ -0,0 +1,804 @@
{
"last_node_id": 16,
"last_link_id": 19,
"nodes": [
{
"id": 1,
"type": "LoadImage",
"pos": [
40,
1890
],
"size": [
390,
432
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
4
]
},
{
"name": "MASK",
"type": "MASK",
"links": []
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"hearthfire_h3/C07_C07.png",
"image"
]
},
{
"id": 2,
"type": "UNETLoader",
"pos": [
40,
40
],
"size": [
390,
300
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
1
]
}
],
"properties": {
"Node name for S&R": "UNETLoader"
},
"widgets_values": [
"minimax_h3_fl2va_pruned_int8_convrot.safetensors",
"default"
]
},
{
"id": 3,
"type": "LoraLoaderModelOnly",
"pos": [
550,
964
],
"size": [
390,
300
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 1
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
5,
7
]
}
],
"properties": {
"Node name for S&R": "LoraLoaderModelOnly"
},
"widgets_values": [
"minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",
1.0
]
},
{
"id": 4,
"type": "CLIPLoader",
"pos": [
40,
2392
],
"size": [
390,
300
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
2
]
}
],
"properties": {
"Node name for S&R": "CLIPLoader"
},
"widgets_values": [
"qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"minimax",
"default"
]
},
{
"id": 5,
"type": "VAELoader",
"pos": [
40,
1150
],
"size": [
390,
300
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
3,
14
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"minimax_h3_video_vae_fp16.safetensors"
]
},
{
"id": 6,
"type": "VAELoader",
"pos": [
40,
1520
],
"size": [
390,
300
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
16
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"minimax_h3_audio_vae_fp32.safetensors"
]
},
{
"id": 7,
"type": "MiniMaxH3ImageToVideo",
"pos": [
550,
1334
],
"size": [
390,
300
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 2
},
{
"name": "vae",
"type": "VAE",
"link": 3
},
{
"name": "first_frame",
"type": "IMAGE",
"link": 4
},
{
"name": "last_frame",
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"name": "positive",
"type": "CONDITIONING",
"links": [
6
]
},
{
"name": "LATENT",
"type": "LATENT",
"links": [
12
]
}
],
"properties": {
"Node name for S&R": "MiniMaxH3ImageToVideo"
},
"widgets_values": [
"For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Keep exactly the first frame original adult man, room geometry, clothing and luminous hand-drawn 2D anime look: fine colored ink contours, clean cel character shading, intricate watercolor backgrounds, ivory window light from left and pale lavender shadows. Organic restrained character acting, naturally timed anticipation and settling, never a rigid puppet or rubbery motion. One continuous shot, no cuts. Wide shot. The same man is standing by the window after watering, cream cup already rests on the sill. His eyes follow the curtain edge, then his LEFT hand reaches and grasps it. He draws the curtain gently across the window during 00:01.000 to 00:03.000. Fabric follows his hand with soft delayed folds, daylight slowly dims to a muted lavender interior; it does not go black. He releases the curtain, pauses, shifts his weight onto his right foot, turns toward the bed at back right and takes two relaxed short steps. Arms swing a little out of phase with the legs, shoulders and hips turn naturally. No sliding feet. Bed, chair and furniture stay fixed. Camera stationary, no speech.\n\noverall_soundscape: Soft curtain rings and cloth, two quiet slipper footsteps, unchanged fan hum. No voices.\n\nnon_diegetic_music: None.",
960,
544,
158
]
},
{
"id": 8,
"type": "BasicGuider",
"pos": [
1060,
1287
],
"size": [
390,
300
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 5
},
{
"name": "conditioning",
"type": "CONDITIONING",
"link": 6
}
],
"outputs": [
{
"name": "GUIDER",
"type": "GUIDER",
"links": [
9
]
}
],
"properties": {
"Node name for S&R": "BasicGuider"
},
"widgets_values": []
},
{
"id": 9,
"type": "RandomNoise",
"pos": [
40,
410
],
"size": [
390,
300
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "NOISE",
"type": "NOISE",
"links": [
8
]
}
],
"properties": {
"Node name for S&R": "RandomNoise"
},
"widgets_values": [
147096411546182,
"fixed"
]
},
{
"id": 10,
"type": "KSamplerSelect",
"pos": [
40,
780
],
"size": [
390,
300
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "SAMPLER",
"type": "SAMPLER",
"links": [
10
]
}
],
"properties": {
"Node name for S&R": "KSamplerSelect"
},
"widgets_values": [
"res_multistep"
]
},
{
"id": 11,
"type": "BasicScheduler",
"pos": [
1060,
917
],
"size": [
390,
300
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 7
}
],
"outputs": [
{
"name": "SIGMAS",
"type": "SIGMAS",
"links": [
11
]
}
],
"properties": {
"Node name for S&R": "BasicScheduler"
},
"widgets_values": [
"simple",
8,
1.0
]
},
{
"id": 12,
"type": "SamplerCustomAdvanced",
"pos": [
1570,
1102
],
"size": [
390,
300
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "noise",
"type": "NOISE",
"link": 8
},
{
"name": "guider",
"type": "GUIDER",
"link": 9
},
{
"name": "sampler",
"type": "SAMPLER",
"link": 10
},
{
"name": "sigmas",
"type": "SIGMAS",
"link": 11
},
{
"name": "latent_image",
"type": "LATENT",
"link": 12
}
],
"outputs": [
{
"name": "output",
"type": "LATENT",
"links": [
13,
15
]
},
{
"name": "denoised_output",
"type": "LATENT",
"links": []
}
],
"properties": {
"Node name for S&R": "SamplerCustomAdvanced"
},
"widgets_values": []
},
{
"id": 13,
"type": "VAEDecode",
"pos": [
2080,
917
],
"size": [
390,
300
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 13
},
{
"name": "vae",
"type": "VAE",
"link": 14
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
17
]
}
],
"properties": {
"Node name for S&R": "VAEDecode"
},
"widgets_values": []
},
{
"id": 14,
"type": "VAEDecodeAudio",
"pos": [
2080,
1287
],
"size": [
390,
300
],
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 15
},
{
"name": "vae",
"type": "VAE",
"link": 16
}
],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
18
]
}
],
"properties": {
"Node name for S&R": "VAEDecodeAudio"
},
"widgets_values": []
},
{
"id": 15,
"type": "CreateVideo",
"pos": [
2590,
1102
],
"size": [
390,
300
],
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 17
},
{
"name": "audio",
"type": "AUDIO",
"link": 18
}
],
"outputs": [
{
"name": "VIDEO",
"type": "VIDEO",
"links": [
19
]
}
],
"properties": {
"Node name for S&R": "CreateVideo"
},
"widgets_values": [
24.0
]
},
{
"id": 16,
"type": "SaveVideo",
"pos": [
3100,
1033
],
"size": [
390,
438
],
"flags": {},
"order": 15,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": 19
}
],
"outputs": [
{
"name": "video",
"type": "VIDEO",
"links": []
}
],
"properties": {
"Node name for S&R": "SaveVideo"
},
"widgets_values": [
"hearthfire_episode/C07_V01",
"mp4",
"h264"
]
}
],
"links": [
[
1,
2,
0,
3,
0,
"MODEL"
],
[
2,
4,
0,
7,
0,
"CLIP"
],
[
3,
5,
0,
7,
1,
"VAE"
],
[
4,
1,
0,
7,
2,
"IMAGE"
],
[
5,
3,
0,
8,
0,
"MODEL"
],
[
6,
7,
0,
8,
1,
"CONDITIONING"
],
[
7,
3,
0,
11,
0,
"MODEL"
],
[
8,
9,
0,
12,
0,
"NOISE"
],
[
9,
8,
0,
12,
1,
"GUIDER"
],
[
10,
10,
0,
12,
2,
"SAMPLER"
],
[
11,
11,
0,
12,
3,
"SIGMAS"
],
[
12,
7,
1,
12,
4,
"LATENT"
],
[
13,
12,
0,
13,
0,
"LATENT"
],
[
14,
5,
0,
13,
1,
"VAE"
],
[
15,
12,
0,
14,
0,
"LATENT"
],
[
16,
6,
0,
14,
1,
"VAE"
],
[
17,
13,
0,
15,
0,
"IMAGE"
],
[
18,
14,
0,
15,
1,
"AUDIO"
],
[
19,
15,
0,
16,
0,
"VIDEO"
]
],
"groups": [
{
"title": "EP01 full episode - MiniMax H3 - native audio",
"bounding": [
-5,
-51,
3540,
2788
],
"color": "#335159",
"font_size": 24
}
],
"config": {},
"extra": {},
"version": 0.4
}
@@ -0,0 +1,57 @@
{
"file": "F:\\project\\小说设计\\06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\C07\\C07_V01_00001_.mp4",
"format": "mov,mp4,m4a,3gp,3g2,mj2",
"duration": 6.583333,
"size_bytes": 857962,
"bitrate": 1042586,
"video": {
"codec": "h264",
"profile": "High",
"width": 960,
"height": 544,
"display_aspect": "30:17",
"fps": 24.0,
"r_frame_rate": "24/1",
"avg_frame_rate": "24/1",
"variable_frame_rate_suspected": false,
"pix_fmt": "yuv420p",
"bit_depth": 8,
"hdr": false,
"hdr_signal": false,
"bt2020_or_hdr": false,
"hdr_format": null,
"dolby_vision": null,
"color_space": "bt709",
"color_primaries": "bt709",
"color_transfer": "iec61966-2-1",
"color_range": "tv",
"rotation": 0,
"nb_frames": 158,
"duration": 6.583333,
"bitrate": 892289
},
"audio": {
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"bitrate": 127918,
"duration": 6.575
},
"subtitle_streams": 0,
"data_streams": 0,
"chapters": [],
"tags": {},
"subtitle_stream_details": [],
"audio_streams": [
{
"index": 0,
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 32000,
"language": "und",
"title": null
}
]
}
@@ -0,0 +1,68 @@
{
"status": "completed",
"output": null,
"dry_run": false,
"commands": [],
"verified": false,
"verification": [],
"platform": "custom",
"checks": [
{
"check": "duration",
"status": "PASS",
"value": "40.00s",
"expected": "any",
"fix": "",
"reason": "",
"kind": "judgement"
},
{
"check": "aspect",
"status": "PASS",
"value": "16:9",
"expected": "any",
"fix": "",
"reason": "",
"kind": "judgement"
},
{
"check": "vfr",
"status": "PASS",
"value": "constant",
"expected": "constant",
"fix": "fit.py --fps N (any re-encode conforms it)",
"reason": "",
"kind": "format"
},
{
"check": "colour",
"status": "PASS",
"value": "bt709/iec61966-2-1",
"expected": "bt709/bt709 tagged (or HDR)",
"fix": "",
"reason": "",
"kind": "format"
},
{
"check": "audio",
"status": "PASS",
"value": "aac 2ch 48000Hz",
"expected": "present",
"fix": "",
"reason": "",
"kind": "format"
},
{
"check": "subtitles",
"status": "WARN",
"value": "none",
"expected": ">= 1 language-tagged subtitle track",
"fix": "caption.py video.mp4 --mode mux --srt subs.srt:en -o video_subs.mkv (streams are copied)",
"reason": "subtitles are optional, but they are the cheapest accessibility win a delivery has",
"kind": "format"
}
],
"failed": 0,
"warnings": 1,
"ok": true
}
@@ -0,0 +1,11 @@
{
"status": "completed",
"output": "06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\第一集_开篇40秒_试看.mp4",
"dry_run": true,
"commands": [
"'C:\\Users\\zhang\\.codex\\tools\\media-bin\\ffmpeg.EXE' -hide_banner -loglevel error -nostdin -y -ss 0.000 -i '06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\第一集_开篇40秒_柔光版V02.mp4' -vf fps=24 -map 0:v:0 -map 0:a:0 -c:v libx264 -preset medium -crf 18 -pix_fmt yuv420p -movflags +faststart -colorspace bt709 -color_primaries bt709 -color_trc bt709 -c:a aac -b:a 192k -t 40.000 '06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\第一集_开篇40秒_试看.mp4'"
],
"verified": false,
"verification": [],
"dropped_non_av_streams": false
}
@@ -0,0 +1,73 @@
{
"status": "completed",
"output": "06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\第一集_开篇40秒_试看.mp4",
"dry_run": false,
"commands": [
"'C:\\Users\\zhang\\.codex\\tools\\media-bin\\ffmpeg.EXE' -hide_banner -loglevel error -nostdin -y -ss 0.000 -i '06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\第一集_开篇40秒_柔光版V02.mp4' -vf fps=24 -map 0:v:0 -map 0:a:0 -c:v libx264 -preset medium -crf 18 -pix_fmt yuv420p -movflags +faststart -colorspace bt709 -color_primaries bt709 -color_trc bt709 -c:a aac -b:a 192k -t 40.000 '06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\第一集_开篇40秒_试看.mp4'"
],
"probe": {
"file": "06_AI动漫制作\\05_生产素材\\视频测试\\2026-09-29_H3_开篇40秒_柔光V02\\第一集_开篇40秒_试看.mp4",
"format": "mov,mp4,m4a,3gp,3g2,mj2",
"duration": 40.0,
"size_bytes": 14336707,
"bitrate": 2867341,
"video": {
"codec": "h264",
"profile": "High",
"width": 1280,
"height": 720,
"display_aspect": "16:9",
"fps": 24.0,
"r_frame_rate": "24/1",
"avg_frame_rate": "24/1",
"variable_frame_rate_suspected": false,
"pix_fmt": "yuv420p",
"bit_depth": 8,
"hdr": false,
"hdr_signal": false,
"bt2020_or_hdr": false,
"hdr_format": null,
"dolby_vision": null,
"color_space": "bt709",
"color_primaries": "bt709",
"color_transfer": "iec61966-2-1",
"color_range": "tv",
"rotation": 0,
"nb_frames": 960,
"duration": 40.0,
"bitrate": 2667321
},
"audio": {
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 48000,
"bitrate": 194088,
"duration": 40.0
},
"subtitle_streams": 0,
"data_streams": 0,
"chapters": [],
"tags": {},
"subtitle_stream_details": [],
"audio_streams": [
{
"index": 0,
"codec": "aac",
"channels": 2,
"channel_layout": "stereo",
"sample_rate": 48000,
"language": "und",
"title": null
}
]
},
"verified": true,
"verification": [
{
"step": "probe",
"ok": true
}
],
"dropped_non_av_streams": false
}

Some files were not shown because too many files have changed in this diff Show More